Google BigQuery

Overview

Google BigQuery is a fully managed, serverless data warehouse that lets you run analytical SQL queries on massive datasets with high speed and scale. With the SquadOS integration, your agents can create and query datasets, run SQL jobs, manage tables, routines, and machine learning models, and control IAM permissions — all through natural language.

Official website: https://cloud.google.com/bigquery
Composio documentation: docs.composio.dev/toolkits/googlebigquery

Authentication

This tool uses OAuth 2.0 (OAUTH2) or a Google Service Account (GOOGLE_SERVICE_ACCOUNT) to connect.

You will need one of the following authentication methods:

Field	Required	Description
Google Account (OAuth 2.0)	Yes	Authorize access via the OAuth flow on the Composio secure connection page.
Service account (JSON)	Yes (alternative)	JSON credentials file from a service account with permissions on the BigQuery project.

How to get credentials

Option 1 — OAuth 2.0 (recommended for personal use)

Go to the Google Cloud Console and sign in.
Make sure the BigQuery API is enabled in your desired project.
When connecting via SquadOS, you will be redirected to authorize OAuth access directly on the Composio secure connection page.

Option 2 — Service Account (recommended for automations)

Go to the Google Cloud Console and select your project.
Navigate to IAM & Admin → Service Accounts.
Click Create Service Account, fill in the name, and assign the BigQuery User and BigQuery Data Editor roles (or the roles appropriate for the desired scope).
After creating, go to the service account → Keys tab → Add Key → Create new key → JSON.
Download the JSON file — this is the value to provide when connecting via service account in SquadOS.

How to connect in SquadOS

Go to Tools in the side menu (/admin/tools).
Open the Available tab and search for Google BigQuery.
Click the card to open the details modal and hit Connect.
You’re taken to the secure connection page hosted by Composio, where you authorize access via OAuth 2.0 or enter the service account credentials.
Once done, you’re sent back to SquadOS with the account connected and the tool available to your agents. (Connection-flow details in Organization Tools.)

Available actions

Cancel BigQuery Job

GOOGLEBIGQUERY_CANCEL_JOB

Tool to cancel a running BigQuery job. This call returns immediately, and you need to poll for the job status to see if the cancel completed successfully. Note that cancelled jobs may still incur costs.

Input parameters

Name	Type	Required	Description
`job_id`	string	Yes	Required. Job ID of the job to cancel.
`location`	string	No	The geographic location of the job. You must specify the location to run the job for the following scenarios: If the location to run a job is not in the `us` or the `eu` multi-regional location. If the job’s location is in a single region (for example, `us-central1`).
`project_id`	string	Yes	Required. Project ID of the job to cancel.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create Capacity Commitment

GOOGLEBIGQUERY_CREATE_CAPACITY_COMMITMENT

Tool to create a new capacity commitment resource in BigQuery Reservation. Use when you need to purchase compute capacity (slots) with a committed period of usage for BigQuery jobs. Supports various commitment plans (FLEX, MONTHLY, ANNUAL, THREE_YEAR) and editions (STANDARD, ENTERPRISE, ENTERPRISE_PLUS).

Input parameters

Name	Type	Required	Description
`plan`	string (`"COMMITMENT_PLAN_UNSPECIFIED"` \| `"FLEX"` \| `"FLEX_FLAT_RATE"` \| `"TRIAL"` \| `"MONTHLY"` \| `"MONTHLY_FLAT_RATE"` \| `"ANNUAL"` \| `"ANNUAL_FLAT_RATE"` \| `"THREE_YEAR"` \| `"NONE"`)	Yes	Required. Capacity commitment plan. Determines the commitment period and pricing.
`parent`	string	Yes	Required. Resource name of the parent reservation. Must be in the format `projects/{project}/locations/{location}` (e.g., `projects/myproject/locations/US`).
`edition`	string (`"EDITION_UNSPECIFIED"` \| `"STANDARD"` \| `"ENTERPRISE"` \| `"ENTERPRISE_PLUS"`)	No	Edition of the capacity commitment.
`slotCount`	string	Yes	Required. Number of slots in this commitment. Must be a positive integer represented as a string.
`renewalPlan`	string	No	Capacity commitment plan types.
`capacityCommitmentId`	string	No	The optional capacity commitment ID. Generated automatically if empty. Must only contain lower case alphanumeric characters or dashes. Max length is 64 characters.
`multiRegionAuxiliary`	boolean	No	Applicable only for commitments located within one of the BigQuery multi-regions (US or EU). If set to true, this commitment is placed in the organization’s secondary region for disaster recovery.
`enforceSingleAdminProjectPerOrg`	boolean	No	If true, fail the request if another project in the organization has a capacity commitment.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create BigQuery Connection

GOOGLEBIGQUERY_CREATE_CONNECTION

Tool to create a new BigQuery connection to external data sources using the BigQuery Connection API. Use when setting up connections to AWS, Azure, Cloud Spanner, Cloud SQL, Salesforce DataCloud, or Apache Spark.

Input parameters

Name	Type	Required	Description
`aws`	object	No	Connection properties specific to Amazon Web Services (AWS).
`azure`	object	No	Container for connection properties specific to Azure.
`spark`	object	No	Container for connection properties to execute stored procedures for Apache Spark.
`parent`	string	Yes	Required. Parent resource name in the format `projects/{project_id}/locations/{location_id}`. Example: `projects/my-project/locations/us-central1`.
`cloudSql`	object	No	Connection properties specific to Cloud SQL.
`kmsKeyName`	string	No	Optional. The Cloud KMS key that is used for encryption.
`description`	string	No	User provided description for the connection.
`cloudSpanner`	object	No	Connection properties specific to Cloud Spanner.
`connectionId`	string	No	Optional. Connection id that should be assigned to the created connection. If not specified, a random connection id will be generated.
`friendlyName`	string	No	User provided display name for the connection.
`cloudResource`	object	No	Container for connection properties for delegation of access to GCP resources.
`salesforceDataCloud`	object	No	Connection properties specific to Salesforce DataCloud.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create Analytics Hub Data Exchange

GOOGLEBIGQUERY_CREATE_DATA_EXCHANGE

Tool to create a new Analytics Hub data exchange for sharing BigQuery datasets. Use when you need to set up a container for data sharing with descriptive information and listings.

Input parameters

Name	Type	Required	Description
`icon`	string	No	Optional. Base64 encoded image representing the data exchange. Max Size: 3.0MiB. Expected image dimensions are 512x512 pixels.
`parent`	string	Yes	Required. The parent resource path of the data exchange in the format `projects/{project}/locations/{location}`. Example: `projects/my-project/locations/US`.
`description`	string	No	Optional. Description of the data exchange. Max length: 2000 bytes.
`displayName`	string	Yes	Required. Human-readable display name of the data exchange. Max length: 63 bytes.
`documentation`	string	No	Optional. Documentation describing the data exchange.
`dataExchangeId`	string	Yes	Required. The ID of the data exchange. Must contain only Unicode letters, numbers (0-9), underscores (_). Max length: 100 bytes.
`primaryContact`	string	No	Optional. Email or URL of the primary point of contact of the data exchange. Max Length: 1000 bytes.
`sharingEnvironmentConfig`	object	No	Sharing environment configuration for data exchange behavior.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create Analytics Hub Listing

GOOGLEBIGQUERY_CREATE_DATAEXCHANGES_LISTINGS

Tool to create a new listing in a BigQuery Analytics Hub data exchange. Use when you need to share a BigQuery dataset with specific subscribers or make it available for discovery. The dataset must exist and be in the same region as the data exchange.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. The parent data exchange resource path in format `projects/{projectId}/locations/{location}/dataExchanges/{dataExchangeId}`. The location must match the dataset location.
`listingId`	string	Yes	Required. The ID to use for the listing. Must contain only Unicode letters, numbers (0-9), underscores (_). Max length: 100 bytes.
`publisher`	object	No	Details of the publisher who owns the listing.
`categories`	array	No	Optional. Categories of the listing. Up to two categories are allowed.
`description`	string	No	Optional. Short description of the listing. Max 2000 bytes.
`displayName`	string	Yes	Required. Human-readable display name of the listing. Max 63 bytes.
`dataProvider`	object	No	Details of the data provider who owns the source data.
`documentation`	string	No	Optional. Documentation describing the listing in detail.
`requestAccess`	string	No	Optional. Email or URL where users can request access to the listing. Max 1000 bytes.
`primaryContact`	string	No	Optional. Email or URL of the primary point of contact for the listing. Max 1000 bytes.
`bigqueryDataset`	object	Yes	Required. The BigQuery dataset source to be shared. This dataset must exist and be in the same region as the data exchange.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create BigQuery Dataset

GOOGLEBIGQUERY_CREATE_DATASET

Tool to create a new BigQuery dataset with explicit location, labels, and description using the BigQuery Datasets API. Use when the workflow needs to set up a staging/warehouse dataset and correctness of region is critical to avoid downstream job location mismatches. Surfaces 409 Already Exists errors cleanly without retrying.

Input parameters

Name	Type	Required	Description
`access`	array	No	Access control list (ACL) for the dataset. If not specified, the dataset inherits project-level permissions.
`labels`	object	No	Labels to organize and categorize the dataset. Labels are key-value pairs. Keys and values must be lowercase, max 63 characters.
`location`	string	Yes	Geographic location where the dataset should reside. This is CRITICAL to avoid location-related query/job errors. Examples: `US`, `EU`, `us-central1`, `europe-west1`.
`dataset_id`	string	Yes	The dataset ID. Must be unique within the project. Use alphanumeric characters, underscores, or hyphens.
`project_id`	string	Yes	The project ID where the dataset will be created. This is used in the URL path, not in the request body.
`description`	string	No	A description of the dataset. Use this to document the dataset’s purpose and contents.
`friendly_name`	string	No	A user-friendly name for the dataset. This is a descriptive label that appears in the BigQuery UI.
`defaultTableExpirationMs`	integer	No	Default lifetime of all tables in the dataset, in milliseconds.
`defaultPartitionExpirationMs`	integer	No	Default lifetime of all partitions in tables in the dataset, in milliseconds.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create Analytics Hub Listing (v2)

GOOGLEBIGQUERY_CREATE_LISTING

Tool to create a new listing in a data exchange using Analytics Hub API. Use when publishing a BigQuery dataset to make it available for subscription by other users or organizations.

Input parameters

Name	Type	Required	Description
`alt`	string (`"json"` \| `"media"` \| `"proto"`)	No	Data format for response.
`key`	string	No	API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
`icon`	string	No	Base64 encoded image representing the listing. Max Size: 3.0MiB. Expected image dimensions are 512x512 pixels.
`xgafv`	string (`"1"` \| `"2"`)	No	V1 error format.
`fields`	string	No	Selector specifying which fields to include in a partial response.
`parent`	string	Yes	Required. The parent resource path of the listing. Format: `projects/{project_id}/locations/{location}/dataExchanges/{data_exchange_id}`.
`callback`	string	No	JSONP callback parameter.
`listingId`	string	No	The ID of the listing to create. If not provided, a random ID will be generated.
`publisher`	object	No	Details of the listing publisher.
`categories`	array	No	Categories of the listing. Up to two categories are allowed.
`quota_user`	string	No	Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
`uploadType`	string	No	Legacy upload protocol for media (e.g. ‘media’, ‘multipart’).
`description`	string	No	Short description of the listing. Max length: 2000 bytes.
`displayName`	string	Yes	Required. Human-readable display name of the listing. Max length: 63 bytes.
`oauth_token`	string	No	OAuth 2.0 token for the current user.
`prettyPrint`	boolean	No	Returns response with indentations and line breaks.
`access_token`	string	No	OAuth access token.
`dataProvider`	object	No	Details of the data provider.
`documentation`	string	No	Documentation describing the listing.
`requestAccess`	string	No	Email or URL of the request access of the listing. Max Length: 1000 bytes.
`primaryContact`	string	No	Email or URL of the primary point of contact of the listing. Max Length: 1000 bytes.
`bigqueryDataset`	object	Yes	Required. Reference to the shared BigQuery dataset. Analytics Hub creates a linked dataset for subscribers when they subscribe to this listing.
`upload_protocol`	string	No	Upload protocol for media (e.g. ‘raw’, ‘multipart’).
`restrictedExportConfig`	object	No	Restricted export configuration for linked dataset.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create BigQuery Data Policy (v2beta1)

GOOGLEBIGQUERY_CREATE_LOCATIONS_DATAPOLICIES

Tool to create a new data policy under a project with specified location using the v2beta1 BigQuery Data Policy API. Use when you need to set up data masking rules or column-level security for sensitive data. The v2beta1 endpoint uses a nested request structure.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. Resource name of the project and location that the data policy will belong to. The format is `projects/{project_number}/locations/{location_id}`. Example: `projects/934040047113/locations/us-central1`.
`dataPolicy`	object	Yes	Required. The data policy configuration containing the policy type, policy tag, and masking rules.
`dataPolicyId`	string	Yes	Required. User-assigned (human readable) ID of the data policy that needs to be unique within a project. Used as {data_policy_id} in part of the resource name. This will also be used as the display name.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create Analytics Hub Query Template

GOOGLEBIGQUERY_CREATE_QUERY_TEMPLATE

Tool to create a new query template in a BigQuery Analytics Hub Data Clean Room (DCR) data exchange. Use when you need to define predefined and approved queries for data clean room use cases. Query templates must be created in DCR data exchanges only.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. The parent resource where this query template will be created. Format: `projects/{project}/locations/{location}/dataExchanges/{dataExchange}`. Note: Query templates require a Data Clean Room (DCR) data exchange.
`routine`	object	Yes	Required. The routine definition containing the query template logic.
`description`	string	No	Optional. Description of the query template explaining its purpose and usage.
`displayName`	string	Yes	Required. Human-readable name of the query template. This name will be shown to subscribers of the data exchange.
`queryTemplateId`	string	Yes	Required. The ID to use for the query template. Must contain only Unicode letters, numbers (0-9), underscores (_). Max length: 100 bytes.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create BigQuery Reservation

GOOGLEBIGQUERY_CREATE_RESERVATION

Tool to create a new BigQuery reservation resource to guarantee compute capacity (slots) for query and pipeline jobs. Use when you need to reserve dedicated compute resources for predictable performance and cost management. Reservations can be configured with autoscaling, concurrency limits, and edition-based features.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. Project, location. E.g., `projects/myproject/locations/US`. The parent resource where the reservation will be created.
`edition`	string (`"EDITION_UNSPECIFIED"` \| `"STANDARD"` \| `"ENTERPRISE"` \| `"ENTERPRISE_PLUS"`)	No	Edition of the reservation.
`autoscale`	object	No	Auto scaling settings for the reservation.
`concurrency`	string	No	Job concurrency target which sets a soft upper bound on the number of jobs that can run concurrently in this reservation. Default value is 0 which means that concurrency target will be automatically computed by the system. Must be a non-negative integer represented as a string.
`slotCapacity`	string	Yes	Required. Baseline slots available to this reservation. A slot is a unit of computational power in BigQuery. Must be a positive integer represented as a string.
`reservationId`	string	No	Optional reservation ID. Maximum length is 64 characters. If not provided, a reservation ID will be generated automatically.
`ignoreIdleSlots`	boolean	No	If false, any query or pipeline job using this reservation will use idle slots from other reservations within the same admin project.
`multiRegionAuxiliary`	boolean	No	Applicable only for reservations located within one of the BigQuery multi-regions (US or EU). If set to true, this reservation is placed in the organization’s secondary region for disaster recovery purposes.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create BigQuery Reservation Assignment

GOOGLEBIGQUERY_CREATE_RESERVATION_ASSIGNMENT

Tool to create a BigQuery reservation assignment that allows a project, folder, or organization to submit jobs using slots from a specified reservation. Use when setting up resource allocation for BigQuery workloads. Note: A resource can only have one assignment per (job_type, location) combination.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. The parent resource name of the assignment. Format: `projects/{project_id}/locations/{location}/reservations/{reservation_id}`. Example: `projects/myproject/locations/US/reservations/team1-prod`.
`jobType`	string (`"JOB_TYPE_UNSPECIFIED"` \| `"PIPELINE"` \| `"QUERY"` \| `"ML_EXTERNAL"` \| `"BACKGROUND"`)	Yes	Required. Which type of jobs will use the reservation.
`assignee`	string	Yes	Required. The resource which will use the reservation. Can be a project, folder, or organization. Format: `projects/{project_id}`, `folders/{folder_id}`, or `organizations/{org_id}`.
`assignmentId`	string	No	Optional assignment ID. Assignment name will be generated automatically if this field is empty. Max length is 64 characters.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create BigQuery Routine

GOOGLEBIGQUERY_CREATE_ROUTINE

Tool to create a new user-defined routine (function or procedure) in a BigQuery dataset. Use when you need to define SQL, JavaScript, Python, Java, or Scala functions/procedures for reusable logic, data transformations, or custom masking. Supports scalar functions, table-valued functions, procedures, and aggregate functions with comprehensive type definitions.

Input parameters

Name	Type	Required	Description
`language`	string (`"LANGUAGE_UNSPECIFIED"` \| `"SQL"` \| `"JAVASCRIPT"` \| `"PYTHON"` \| `"JAVA"` \| `"SCALA"`)	No	Programming language of the routine.
`arguments`	array	No	Optional. Input/output arguments for the routine.
`dataset_id`	string	Yes	Required. Dataset ID where the routine will be created. Used in the URL path.
`project_id`	string	Yes	Required. Project ID where the routine will be created. Used in the URL path.
`returnType`	object	No	Data type of a BigQuery field or function argument.
`strictMode`	boolean	No	Optional. If TRUE (default), the procedure body is checked for errors like non-existent tables.
`description`	string	No	Optional. A description of the routine.
`routineType`	string (`"ROUTINE_TYPE_UNSPECIFIED"` \| `"SCALAR_FUNCTION"` \| `"PROCEDURE"` \| `"TABLE_VALUED_FUNCTION"` \| `"AGGREGATE_FUNCTION"`)	Yes	Required. The type of routine.
`securityMode`	string (`"SECURITY_MODE_UNSPECIFIED"` \| `"DEFINER"` \| `"INVOKER"`)	No	Security mode of the routine.
`sparkOptions`	object	No	Options for user-defined Spark routines.
`definitionBody`	string	Yes	Required. The body of the routine. For SQL functions, this is the expression in the AS clause (excluding parentheses). For JavaScript, it’s the evaluated string in the AS clause.
`returnTableType`	object	No	A table type for table-valued functions.
`determinismLevel`	string (`"DETERMINISM_LEVEL_UNSPECIFIED"` \| `"DETERMINISTIC"` \| `"NOT_DETERMINISTIC"`)	No	Determinism level for JavaScript UDFs.
`routineReference`	object	Yes	Required. Reference containing projectId, datasetId, and routineId for the new routine.
`importedLibraries`	array	No	Optional. For JavaScript routines, paths of imported JavaScript libraries.
`dataGovernanceType`	string (`"DATA_GOVERNANCE_TYPE_UNSPECIFIED"` \| `"DATA_MASKING"`)	No	Data governance type for the routine.
`remoteFunctionOptions`	object	No	Options for remote user-defined functions.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Create BigQuery Table

GOOGLEBIGQUERY_CREATE_TABLE

Tool to create a new, empty table in a BigQuery dataset. Use when setting up data infrastructure for standard tables, external tables, views, or materialized views. Supports partitioning, clustering, and encryption configuration.

Input parameters

Name	Type	Required	Description
`view`	object	No	Logical view definition.
`labels`	object	No	Labels to organize tables. Keys and values must be lowercase, max 63 characters, starting with a letter.
`schema`	object	No	Schema of a table defining its fields/columns.
`clustering`	object	No	Clustering configuration for a table.
`dataset_id`	string	Yes	The dataset ID where the table will be created. Used in the URL path.
`project_id`	string	Yes	The project ID where the table will be created. Used in the URL path.
`description`	string	No	A user-friendly description of the table.
`friendlyName`	string	No	A descriptive name for the table shown in the BigQuery UI.
`expirationTime`	string	No	Time when the table expires, in milliseconds since epoch.
`tableReference`	object	Yes	Reference identifying the table. Must match project_id and dataset_id from the path.
`defaultCollation`	string	No	Default collation for new STRING fields. Options: `und:ci` (case insensitive), `''` (case sensitive, default).
`materializedView`	object	No	Materialized view definition and configuration.
`timePartitioning`	object	No	Time-based partitioning configuration for a table.
`rangePartitioning`	object	No	Range-based partitioning configuration for a table.
`requirePartitionFilter`	boolean	No	If true, queries over this table require a partition filter for partition elimination.
`encryptionConfiguration`	object	No	Encryption configuration for a table.
`externalDataConfiguration`	object	No	Configuration for external data sources.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Delete BigQuery Dataset

GOOGLEBIGQUERY_DELETE_DATASET

Tool to delete a BigQuery dataset specified by datasetId via the datasets.delete API. Before deletion, you must delete all tables unless deleteContents=True is specified. Use when cleaning up test datasets or removing unused data warehouses.

Input parameters

Name	Type	Required	Description
`dataset_id`	string	Yes	Required. Dataset ID of dataset being deleted.
`project_id`	string	Yes	Required. Project ID of the dataset being deleted.
`delete_contents`	boolean	No	If True, delete all the tables in the dataset. If False and the dataset contains tables, the request will fail. Default is False.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Delete BigQuery Job Metadata

GOOGLEBIGQUERY_DELETE_JOB_METADATA

Tool to delete the metadata of a BigQuery job. Use when you need to remove job metadata from the system. If this is a parent job with child jobs, metadata from all child jobs will be deleted as well.

Input parameters

Name	Type	Required	Description
`job_id`	string	Yes	Required. Job ID of the job for which metadata is to be deleted. If this is a parent job which has child jobs, the metadata from all child jobs will be deleted as well. Direct deletion of the metadata of child jobs is not allowed.
`location`	string	No	The geographic location of the job. Required for jobs in certain regions.
`project_id`	string	Yes	Required. Project ID of the job for which metadata is to be deleted.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Delete BigQuery ML Model

GOOGLEBIGQUERY_DELETE_MODEL

Tool to delete a BigQuery ML model from a dataset. Use when you need to remove a trained machine learning model permanently. The operation deletes the model and cannot be undone.

Input parameters

Name	Type	Required	Description
`model_id`	string	Yes	Required. Model ID of the model to delete.
`dataset_id`	string	Yes	Required. Dataset ID of the model to delete.
`project_id`	string	Yes	Required. Project ID of the model to delete.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Delete BigQuery Routine

GOOGLEBIGQUERY_DELETE_ROUTINE

Tool to delete a BigQuery routine by its ID. Use when you need to remove a stored procedure, user-defined function, or table function from a dataset. This operation is irreversible.

Input parameters

Name	Type	Required	Description
`dataset_id`	string	Yes	Required. Dataset ID of the routine to delete.
`project_id`	string	Yes	Required. Project ID of the routine to delete.
`routine_id`	string	Yes	Required. Routine ID of the routine to delete.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Delete BigQuery Table

GOOGLEBIGQUERY_DELETE_TABLE

Tool to delete a BigQuery table from a dataset. Use when you need to remove a table and all its data permanently. The operation deletes all data in the table and cannot be undone.

Input parameters

Name	Type	Required	Description
`table_id`	string	Yes	Required. Table ID of the table to delete.
`dataset_id`	string	Yes	Required. Dataset ID of the table to delete.
`project_id`	string	Yes	Required. Project ID of the table to delete.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery ML Model

GOOGLEBIGQUERY_GET_BIGQUERY_MODEL

Tool to retrieve a specific BigQuery ML model resource by model ID. Use when you need detailed information about a trained machine learning model including its configuration, training runs, hyperparameters, and evaluation metrics.

Input parameters

Name	Type	Required	Description
`model_id`	string	Yes	Required. Model ID of the requested model.
`dataset_id`	string	Yes	Required. Dataset ID of the requested model.
`project_id`	string	Yes	Required. Project ID of the requested model.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Connection IAM Policy

GOOGLEBIGQUERY_GET_CONNECTION_IAM_POLICY

Tool to get the IAM access control policy for a BigQuery connection resource. Returns an empty policy if the resource exists but has no policy set. Use this to check who has access to a specific connection before modifying permissions.

Input parameters

Name	Type	Required	Description
`options`	object	No	Optional settings for GetIamPolicy request. Specify requestedPolicyVersion if you need a specific policy version format.
`resource`	string	Yes	REQUIRED: The resource for which the policy is being requested. Format: `projects/{project}/locations/{location}/connections/{connection}`. Example: `projects/my-project/locations/us/connections/my-connection`

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Dataset Metadata

GOOGLEBIGQUERY_GET_DATASET

Tool to retrieve BigQuery dataset metadata including location via the datasets.get API. Use this before creating jobs/queries if the workflow has been failing with location mismatch to confirm the dataset’s region and correct the job location accordingly.

Input parameters

Name	Type	Required	Description
`dataset_id`	string	Yes	Dataset ID of the requested dataset.
`project_id`	string	Yes	Project ID of the requested dataset.
`dataset_view`	string (`"DATASET_VIEW_UNSPECIFIED"` \| `"METADATA"` \| `"ACL"` \| `"FULL"`)	No	Optional view specifying which dataset information to return. DATASET_VIEW_UNSPECIFIED defaults to FULL.
`access_policy_version`	integer	No	Version of access policy schema to fetch. Valid values: 0, 1, 3. Use version 3 for conditional access policy bindings. If unset, defaults to version 1.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Job

GOOGLEBIGQUERY_GET_JOB

Tool to retrieve information about a specific BigQuery job. Returns job configuration, status, and statistics. Use this to check job status after running queries or to get details about job execution.

Input parameters

Name	Type	Required	Description
`job_id`	string	Yes	Required. Job ID of the requested job.
`location`	string	No	The geographic location of the job. You must specify the location to run the job for the following scenarios: If the location to run a job is not in the `us` or the `eu` multi-regional location, or if the job’s location is in a single region (for example, `us-central1`).
`project_id`	string	Yes	Required. Project ID of the requested job.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Query Results

GOOGLEBIGQUERY_GET_QUERY_RESULTS

Tool to get the results of a BigQuery query job via RPC. Use this to retrieve results after running a query, or to check job completion status and fetch paginated results.

Input parameters

Name	Type	Required	Description
`alt`	string (`"json"` \| `"media"` \| `"proto"`)	No	Data format for response enum.
`key`	string	No	API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
`jobId`	string	Yes	Required. Job ID of the query job.
`xgafv`	string (`"1"` \| `"2"`)	No	V1 error format enum.
`fields`	string	No	Selector specifying which fields to include in a partial response.
`callback`	string	No	JSONP callback parameter.
`location`	string	No	The geographic location of the job.
`pageToken`	string	No	Page token, returned by a previous call, to request the next page of results.
`projectId`	string	Yes	Required. Project ID of the query job.
`quotaUser`	string	No	Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
`timeoutMs`	integer	No	Optional: Specifies the maximum amount of time, in milliseconds, that the client is willing to wait for the query to complete. By default, this limit is 10 seconds (10,000 milliseconds).
`maxResults`	integer	No	Maximum number of results to read.
`startIndex`	string	No	Zero-based index of the starting row.
`uploadType`	string	No	Legacy upload protocol for media (e.g. “media”, “multipart”).
`oauth_token`	string	No	OAuth 2.0 token for the current user.
`prettyPrint`	boolean	No	Returns response with indentations and line breaks.
`access_token`	string	No	OAuth access token.
`upload_protocol`	string	No	Upload protocol for media (e.g. “raw”, “multipart”).
`formatOptions.useInt64Timestamp`	boolean	No	Optional. Output timestamp as usec int64. Default is false.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Routine

GOOGLEBIGQUERY_GET_ROUTINE

Tool to retrieve a BigQuery routine (user-defined function or stored procedure) by its ID. Use to inspect routine definitions, arguments, return types, and metadata.

Input parameters

Name	Type	Required	Description
`read_mask`	string	No	If set, only the Routine fields in the field mask are returned in the response. If unset, all Routine fields are returned.
`dataset_id`	string	Yes	Required. Dataset ID of the requested routine.
`project_id`	string	Yes	Required. Project ID of the requested routine.
`routine_id`	string	Yes	Required. Routine ID of the requested routine.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Routine IAM Policy

GOOGLEBIGQUERY_GET_ROUTINE_IAM_POLICY

Tool to retrieve the IAM access control policy for a BigQuery routine resource. Returns an empty policy if the routine exists but has no policy set. Use this to check current access permissions before modifying them.

Input parameters

Name	Type	Required	Description
`options`	object	No	Optional settings for GetIamPolicy request. Specify requestedPolicyVersion if you need a specific policy version format.
`dataset_id`	string	Yes	Required. The ID of the dataset containing the routine.
`project_id`	string	Yes	Required. The ID of the project containing the routine.
`routine_id`	string	Yes	Required. The ID of the routine to get IAM policy for.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Service Account

GOOGLEBIGQUERY_GET_SERVICE_ACCOUNT

Tool to get the service account for a project used for interactions with Google Cloud KMS. Use when you need to retrieve the BigQuery service account email for KMS encryption configuration or key access permissions.

Input parameters

Name	Type	Required	Description
`alt`	string (`"json"` \| `"media"` \| `"proto"`)	No	Data format for response.
`key`	string	No	API key.
`xgafv`	string (`"1"` \| `"2"`)	No	V1 error format.
`fields`	string	No	Selector specifying which fields to include in a partial response.
`callback`	string	No	JSONP callback.
`project_id`	string	Yes	Required. ID of the project.
`quota_user`	string	No	Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
`uploadType`	string	No	Legacy upload protocol for media (e.g. ‘media’, ‘multipart’).
`oauth_token`	string	No	OAuth 2.0 token for the current user.
`prettyPrint`	boolean	No	Returns response with indentations and line breaks.
`access_token`	string	No	OAuth access token.
`upload_protocol`	string	No	Upload protocol for media (e.g. ‘raw’, ‘multipart’).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Table IAM Policy

GOOGLEBIGQUERY_GET_TABLE_IAM_POLICY

Tool to retrieve the IAM access control policy for a BigQuery table resource. Returns an empty policy if the resource exists but has no policy set. Use this to check current access permissions before modifying them.

Input parameters

Name	Type	Required	Description
`resource`	string	Yes	REQUIRED: The resource for which the policy is being requested. Format: `projects/{projectId}/datasets/{datasetId}/tables/{tableId}`.
`requested_policy_version`	integer	No	Optional. The maximum policy version that will be used to format the policy. Valid values are 0, 1, and 3. Policies with conditional role bindings must specify version 3. If unset, defaults to version 1.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Get BigQuery Table Schema

GOOGLEBIGQUERY_GET_TABLE_SCHEMA

Tool to fetch a BigQuery table’s schema and metadata without querying row data. Use before generating SQL queries to avoid column name typos and confirm field types and nullable modes. This is especially useful when INFORMATION_SCHEMA access is restricted.

Input parameters

Name	Type	Required	Description
`table_id`	string	Yes	The table ID to retrieve schema and metadata for.
`dataset_id`	string	Yes	The dataset ID containing the table.
`project_id`	string	Yes	The project ID containing the dataset.
`selected_fields`	string	No	Comma-separated list of fields to return (e.g., `schema,numRows,type`). If not specified, returns all fields.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Insert Data into BigQuery Table

GOOGLEBIGQUERY_INSERT_ALL

Tool to stream data into BigQuery one record at a time without running a load job. Use when you need immediate data availability or inserting small batches. Supports row-level deduplication via insertId and error handling via skipInvalidRows.

Input parameters

Name	Type	Required	Description
`rows`	array	Yes	Required. Array of rows to insert. Each row contains the data to be inserted as a JSON object. At least one row must be provided.
`traceId`	string	No	Optional. Unique request trace ID for debugging. Case-sensitive, up to 36 ASCII characters. A UUID is recommended.
`table_id`	string	Yes	Required. Table ID of the destination table.
`dataset_id`	string	Yes	Required. Dataset ID of the destination table.
`project_id`	string	Yes	Required. Project ID of the destination table.
`templateSuffix`	string	No	Optional. If specified, treats the destination table as a base template and inserts rows into an instance table named `{destination}{templateSuffix}`. Useful for table sharding patterns.
`skipInvalidRows`	boolean	No	Optional. If true, insert all valid rows even if some rows are invalid. If false (default), the entire request fails if any row is invalid.
`ignoreUnknownValues`	boolean	No	Optional. If true, accept rows with values that don’t match the schema and ignore the unknown values. If false (default), treat unknown values as errors.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Insert BigQuery Job

GOOGLEBIGQUERY_INSERT_JOB

Tool to start a new asynchronous BigQuery job (query, load, extract, or copy). Use when you need to run a query as a job, load data from Cloud Storage, extract table data to GCS, or copy tables. For dry-run validation without execution, set dryRun to true in configuration.

Input parameters

Name	Type	Required	Description
`project_id`	string	Yes	Project ID of project that will be billed for the job. This is used in the URL path.
`jobReference`	object	No	Job reference identifying the job.
`configuration`	object	Yes	Required. Job configuration. Specify exactly one of: query, load, extract, or copy in the configuration object.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Insert BigQuery Job with Upload

GOOGLEBIGQUERY_INSERT_JOB_WITH_UPLOAD

Tool to start a new BigQuery load job with file upload. Uploads a file (CSV, JSON, etc.) and loads it into a BigQuery table in a single operation. Use when you need to upload data from a local file directly to BigQuery rather than loading from Cloud Storage.

Input parameters

Name	Type	Required	Description
`project_id`	string	Yes	Project ID that will be billed for the job. Used in the URL path.
`jobReference`	object	No	Optional job reference for the upload job.
`configuration`	object	Yes	Job configuration containing load settings (schema, destination table, format, etc.).
`file_to_upload`	object	Yes	File to upload to BigQuery. The file content will be loaded according to the sourceFormat specified in configuration.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List Analytics Hub Listings

GOOGLEBIGQUERY_LIST_ANALYTICS_HUB_LISTINGS

Tool to list all listings in a given Analytics Hub data exchange. Use when you need to discover available data listings within a specific data exchange that can be subscribed to for data sharing.

Input parameters

Name	Type	Required	Description
`alt`	string (`"json"` \| `"media"` \| `"proto"`)	No	Data format for response.
`key`	string	No	API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
`xgafv`	string (`"1"` \| `"2"`)	No	V1 error format.
`fields`	string	No	Selector specifying which fields to include in a partial response.
`parent`	string	Yes	Required. The parent resource path of the listing. Format: `projects/{project_id}/locations/{location}/dataExchanges/{data_exchange_id}`.
`callback`	string	No	JSONP callback parameter.
`pageSize`	integer	No	The maximum number of results to return in a single response page.
`pageToken`	string	No	Page token, returned by a previous call, to request the next page of results.
`quota_user`	string	No	Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
`uploadType`	string	No	Legacy upload protocol for media (e.g. ‘media’, ‘multipart’).
`oauth_token`	string	No	OAuth 2.0 token for the current user.
`prettyPrint`	boolean	No	Returns response with indentations and line breaks.
`access_token`	string	No	OAuth access token.
`upload_protocol`	string	No	Upload protocol for media (e.g. ‘raw’, ‘multipart’).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Connections

GOOGLEBIGQUERY_LIST_BIG_QUERY_CONNECTIONS

Tool to list BigQuery connections in a given project and location. Use when you need to discover available external data source connections (Cloud SQL, AWS, Azure, Spark, etc.) configured for BigQuery.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. Parent resource name. Must be in the form: `projects/{project_id}/locations/{location_id}`. Example: `projects/my-project/locations/us-central1`
`pageSize`	integer	No	Maximum number of connections to return per page.
`pageToken`	string	No	Page token for pagination. Use the nextPageToken from a previous response to get the next page of results.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Capacity Commitments

GOOGLEBIGQUERY_LIST_CAPACITY_COMMITMENTS

Tool to list all capacity commitments for the admin project. Use when you need to view purchased compute capacity slots and their commitment details (plan, state, duration).

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. Resource name of the parent reservation. E.g., `projects/myproject/locations/US`
`page_size`	integer	No	The maximum number of items to return.
`page_token`	string	No	The next_page_token value returned from a previous List request, if any.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List Data Exchange Listings

GOOGLEBIGQUERY_LIST_DATAEXCHANGES_LISTINGS

Tool to list all listings in a given Analytics Hub data exchange using the v1beta1 API. Use when you need to discover available data listings within a specific data exchange that can be subscribed to for data sharing.

Input parameters

Name	Type	Required	Description
`alt`	string (`"json"` \| `"media"` \| `"proto"`)	No	Data format for response.
`key`	string	No	API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
`xgafv`	string (`"1"` \| `"2"`)	No	V1 error format.
`fields`	string	No	Selector specifying which fields to include in a partial response.
`parent`	string	Yes	Required. The parent resource path of the listing. Format: `projects/{project_id}/locations/{location}/dataExchanges/{data_exchange_id}`.
`callback`	string	No	JSONP callback parameter.
`pageSize`	integer	No	The maximum number of results to return in a single response page.
`pageToken`	string	No	Page token, returned by a previous call, to request the next page of results.
`quota_user`	string	No	Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
`uploadType`	string	No	Legacy upload protocol for media (e.g. ‘media’, ‘multipart’).
`oauth_token`	string	No	OAuth 2.0 token for the current user.
`prettyPrint`	boolean	No	Returns response with indentations and line breaks.
`access_token`	string	No	OAuth access token.
`upload_protocol`	string	No	Upload protocol for media (e.g. ‘raw’, ‘multipart’).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Datasets

GOOGLEBIGQUERY_LIST_DATASETS

Tool to list datasets in a specific BigQuery project, including dataset locations. Use after identifying an accessible project to discover available datasets and their locations before querying. The dataset location is critical for avoiding location-related query/job errors.

Input parameters

Name	Type	Required	Description
`all`	boolean	No	Whether to list all datasets, including hidden ones. Defaults to false.
`filter`	string	No	Filter datasets by label in the format `labels.key:value`. Multiple filters can be ANDed together by connecting with a space.
`page_token`	string	No	Page token for pagination.
`project_id`	string	Yes	The project ID containing the datasets.
`max_results`	integer	No	Maximum number of datasets to return per page.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Jobs

GOOGLEBIGQUERY_LIST_JOBS

Tool to list all jobs that you started in a BigQuery project. Job information is available for a six month period after creation. Jobs are sorted in reverse chronological order by creation time. Use to monitor query execution, track job statuses, and retrieve job history.

Input parameters

Name	Type	Required	Description
`all_users`	boolean	No	Whether to display jobs owned by all users in the project. Default False. Requires Is Owner project role to set to true.
`page_token`	string	No	Page token, returned by a previous call, to request the next page of results.
`project_id`	string	Yes	Project ID of the jobs to list.
`projection`	string (`"full"` \| `"minimal"`)	No	Restrict information returned to a set of selected fields.
`max_results`	integer	No	The maximum number of results to return in a single response page.
`state_filter`	array	No	Filter for job state. Can include values like `done`, `pending`, `running`. Multiple states can be specified.
`parent_job_id`	string	No	If set, show only child jobs of the specified parent. Otherwise, show all top-level jobs.
`max_creation_time`	string	No	Max value for job creation time, in milliseconds since the POSIX epoch.
`min_creation_time`	string	No	Min value for job creation time, in milliseconds since the POSIX epoch.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Data Transfer Locations

GOOGLEBIGQUERY_LIST_LOCATIONS

Tool to list information about supported locations for BigQuery Data Transfer Service. Use when you need to discover available regions/locations where BigQuery Data Transfer operations can be performed.

Input parameters

Name	Type	Required	Description
`name`	string	Yes	The resource that owns the locations collection, if applicable. Format: `projects/{project_id}`.
`filter`	string	No	A filter to narrow down results to a preferred subset.
`pageSize`	integer	No	The maximum number of results to return.
`pageToken`	string	No	A page token received from the next_page_token field in the response.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List Connections in Location

GOOGLEBIGQUERY_LIST_LOCATIONS_CONNECTIONS

Tool to list BigQuery connections in a given project and location using the v1beta1 API. Use when you need to discover available external data source connections (Cloud SQL, AWS, Azure, Spark, etc.) configured for BigQuery in a specific location.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. Parent resource name. Must be in the form: `projects/{project_id}/locations/{location_id}`. Example: `projects/my-project/locations/us`
`pageToken`	string	No	Page token for pagination.
`maxResults`	integer	Yes	Required. Maximum number of connections to return per page.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Location Data Policies

GOOGLEBIGQUERY_LIST_LOCATIONS_DATAPOLICIES

Tool to list all data policies in a specified parent project and location using the v2beta1 API. Use when you need to discover data masking policies and column-level security policies configured for BigQuery datasets.

Input parameters

Name	Type	Required	Description
`filter`	string	No	Filters the data policies by policy tags that they are associated with. Currently filter only supports `policy_tag` based filtering and OR based predicates.
`parent`	string	Yes	Required. Resource name of the project for which to list data policies. Format is `projects/{project}/locations/{location}`.
`pageSize`	integer	No	The maximum number of data policies to return. Must be a value between 1 and 1000. If not set, defaults to 50.
`pageToken`	string	No	The nextPageToken value returned from a previous list request, if any.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Models

GOOGLEBIGQUERY_LIST_MODELS

Tool to list all BigQuery ML models in a specified dataset. Requires READER dataset role. Use this to discover available models before getting detailed information via models.get method.

Input parameters

Name	Type	Required	Description
`dataset_id`	string	Yes	Required. Dataset ID of the models to list.
`page_token`	string	No	Page token for pagination, returned by a previous call.
`project_id`	string	Yes	Required. Project ID of the models to list.
`max_results`	integer	No	Maximum number of models to return per page.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List Organization Data Exchanges

GOOGLEBIGQUERY_LIST_ORGANIZATION_DATA_EXCHANGES

Tool to list all data exchanges from projects in a given organization and location using Analytics Hub API. Use when you need to discover available data exchanges within an organization that can be used for data sharing.

Input parameters

Name	Type	Required	Description
`alt`	string (`"json"` \| `"media"` \| `"proto"`)	No	Data format for response.
`key`	string	No	API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
`xgafv`	string (`"1"` \| `"2"`)	No	V1 error format.
`fields`	string	No	Selector specifying which fields to include in a partial response.
`callback`	string	No	JSONP callback parameter.
`pageSize`	integer	No	The maximum number of results to return in a single response page.
`pageToken`	string	No	Page token, returned by a previous call, to request the next page of results.
`quota_user`	string	No	Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
`uploadType`	string	No	Legacy upload protocol for media (e.g. ‘media’, ‘multipart’).
`oauth_token`	string	No	OAuth 2.0 token for the current user.
`prettyPrint`	boolean	No	Returns response with indentations and line breaks.
`access_token`	string	No	OAuth access token.
`organization`	string	Yes	Required. The organization resource path of the projects containing DataExchanges. Format: `organizations/{organization_id}/locations/{location}`.
`upload_protocol`	string	No	Upload protocol for media (e.g. ‘raw’, ‘multipart’).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Projects

GOOGLEBIGQUERY_LIST_PROJECTS

Tool to list BigQuery projects to which the user has been granted any project role. Returns projects with at least READ access. For enhanced capabilities, consider using the Resource Manager API.

Input parameters

Name	Type	Required	Description
`page_token`	string	No	Page token returned by a previous call, to request the next page of results.
`max_results`	integer	No	Maximum number of projects to return per page. If not set, returns all results up to 50 per page.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List Analytics Hub Query Templates

GOOGLEBIGQUERY_LIST_QUERY_TEMPLATES

Tool to list all query templates in a given Analytics Hub data exchange. Use when you need to discover available query templates that define predefined and approved queries for data clean room use cases.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. The parent resource path of the QueryTemplates. Format: `projects/{project}/locations/{location}/dataExchanges/{dataExchange}`.
`pageSize`	integer	No	The maximum number of results to return in a single response page.
`pageToken`	string	No	Page token, returned by a previous call, to request the next page of results.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Reservation Assignments

GOOGLEBIGQUERY_LIST_RESERVATION_ASSIGNMENTS

Tool to list BigQuery reservation assignments. Only explicitly created assignments will be returned (no expansion or merge happens). Use wildcard ”-” in parent path to list assignments across all reservations in a location.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. The parent resource name of the reservation. Format: `projects/{project_id}/locations/{location}/reservations/{reservation_id}` or `projects/{project_id}/locations/{location}/reservations/-` (wildcard to list assignments across all reservations).
`page_size`	integer	No	Maximum number of assignments to return per page.
`page_token`	string	No	Page token from a previous ListAssignments response.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Reservation Groups

GOOGLEBIGQUERY_LIST_RESERVATION_GROUPS

Tool to list all BigQuery reservation groups for a project in a specified location. Use when you need to discover available reservation groups which serve as containers for reservations.

Input parameters

Name	Type	Required	Description
`parent`	string	Yes	Required. The parent resource name containing project and location in the format `projects/{projectId}/locations/{location}`.
`page_size`	integer	No	The maximum number of items to return per page.
`page_token`	string	No	The next_page_token value returned from a previous List request, if any.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Reservations

GOOGLEBIGQUERY_LIST_RESERVATIONS

Tool to list all BigQuery reservations for a project in a specified location. Use when you need to discover available reservations or view reservation details including slot capacity and autoscale configuration.

Input parameters

Name	Type	Required	Description
`alt`	string (`"json"` \| `"media"` \| `"proto"`)	No	Data format for response.
`key`	string	No	API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
`xgafv`	string (`"1"` \| `"2"`)	No	V1 error format.
`fields`	string	No	Selector specifying which fields to include in a partial response.
`parent`	string	Yes	Required. The parent resource name containing project and location, e.g.: `projects/myproject/locations/US`. The location must be specified (e.g., US, EU, us-central1).
`callback`	string	No	JSONP
`page_size`	integer	No	The maximum number of items to return per page.
`page_token`	string	No	The next_page_token value returned from a previous List request, if any.
`quota_user`	string	No	Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
`oauth_token`	string	No	OAuth 2.0 token for the current user.
`upload_type`	string	No	Legacy upload protocol for media (e.g. ‘media’, ‘multipart’).
`access_token`	string	No	OAuth access token.
`pretty_print`	boolean	No	Returns response with indentations and line breaks.
`upload_protocol`	string	No	Upload protocol for media (e.g. ‘raw’, ‘multipart’).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Routines

GOOGLEBIGQUERY_LIST_ROUTINES

Tool to list all routines (user-defined functions and stored procedures) in a BigQuery dataset. Requires the READER dataset role. Use this to discover available routines before executing or inspecting them.

Input parameters

Name	Type	Required	Description
`filter`	string	No	If set, then only the Routines matching this filter are returned. The supported format is `routineType:{RoutineType}`, where `{RoutineType}` is a RoutineType enum. For example: `routineType:SCALAR_FUNCTION`.
`readMask`	string	No	If set, then only the Routine fields in the field mask, as well as project_id, dataset_id and routine_id, are returned in the response.
`pageToken`	string	No	Page token, returned by a previous call, to request the next page of results.
`dataset_id`	string	Yes	Required. Dataset ID of the routines to list.
`maxResults`	integer	No	The maximum number of results to return in a single response page.
`project_id`	string	Yes	Required. Project ID of the routines to list.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Row Access Policies

GOOGLEBIGQUERY_LIST_ROW_ACCESS_POLICIES

Tool to list all row access policies on a specified BigQuery table. Use when you need to discover which row-level security policies are applied to a table and their filter predicates.

Input parameters

Name	Type	Required	Description
`table_id`	string	Yes	Required. Table ID of the table to list row access policies.
`page_size`	integer	No	The maximum number of results to return in a single response page.
`dataset_id`	string	Yes	Required. Dataset ID of row access policies to list.
`page_token`	string	No	Page token, returned by a previous call, to request the next page of results.
`project_id`	string	Yes	Required. Project ID of the row access policies to list.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Table Data

GOOGLEBIGQUERY_LIST_TABLE_DATA

Tool to list the content of a BigQuery table in rows via the REST API. Use this to retrieve actual data from a table without writing SQL queries. Returns paginated results with row data in the native BigQuery format.

Input parameters

Name	Type	Required	Description
`table_id`	string	Yes	Required. Table ID of the table to list.
`dataset_id`	string	Yes	Required. Dataset ID of the table to list.
`page_token`	string	No	To retrieve the next page of table data, set this field to the string provided in the pageToken field of the response body from your previous call to tabledata.list.
`project_id`	string	Yes	Required. Project ID of the table to list.
`max_results`	integer	No	Row limit of the table. Maximum number of rows to return per page.
`start_index`	string	No	Start row index of the table.
`selected_fields`	string	No	Subset of fields to return, supports select into sub fields. Example: `selected_fields = 'a,e.d.f'`.
`format_options_use_int64_timestamp`	boolean	No	Optional. Output timestamp as usec int64. Default is false.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

List BigQuery Tables

GOOGLEBIGQUERY_LIST_TABLES

Tool to list tables in a BigQuery dataset via the REST API. Use this early in exploration to discover accessible tables without relying on INFORMATION_SCHEMA, especially when SQL-based metadata queries are blocked or restricted. This provides a deterministic inventory of tables even when dataset-level permissions prevent INFORMATION_SCHEMA access.

Input parameters

Name	Type	Required	Description
`dataset_id`	string	Yes	The dataset ID to list tables from.
`page_token`	string	No	Page token for pagination.
`project_id`	string	Yes	The project ID containing the dataset.
`max_results`	integer	No	Maximum number of tables to return per page.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Patch BigQuery Dataset

GOOGLEBIGQUERY_PATCH_DATASET

Tool to update an existing BigQuery dataset using RFC5789 PATCH semantics. Only replaces fields provided in the request, leaving other fields unchanged. Use when you need to modify dataset properties like description, labels, expiration settings, or access controls without affecting other configuration.

Input parameters

Name	Type	Required	Description
`access`	array	No	Optional. An array of objects that define dataset access for one or more entities.
`labels`	object	No	The labels associated with this dataset. You can use these to organize and group your datasets.
`location`	string	No	The geographic location where the dataset should reside.
`dataset_id`	string	Yes	Required. Dataset ID of the dataset being updated.
`project_id`	string	Yes	Required. Project ID of the dataset being updated.
`description`	string	No	Optional. A user-friendly description of the dataset.
`friendlyName`	string	No	Optional. A descriptive name for the dataset.
`datasetReference`	object	No	Dataset reference for patching.
`defaultCollation`	string	No	Optional. Defines the default collation specification of future tables created in the dataset. Supported values: `und:ci` (case insensitive) or `''` (case sensitive).
`isCaseInsensitive`	boolean	No	Optional. TRUE if the dataset and its table names are case-insensitive, otherwise FALSE.
`maxTimeTravelHours`	string	No	Optional. Defines the time travel window in hours. The value can be from 48 to 168 hours (2 to 7 days).
`defaultRoundingMode`	string (`"ROUNDING_MODE_UNSPECIFIED"` \| `"ROUND_HALF_AWAY_FROM_ZERO"` \| `"ROUND_HALF_EVEN"`)	No	Optional. Defines the default rounding mode specification of new tables created within this dataset.
`linkedDatasetSource`	object	No	Linked dataset source configuration.
`storageBillingModel`	string (`"STORAGE_BILLING_MODEL_UNSPECIFIED"` \| `"LOGICAL"` \| `"PHYSICAL"`)	No	Optional. Updates storage_billing_model for the dataset.
`defaultTableExpirationMs`	string	No	Optional. The default lifetime of all tables in the dataset, in milliseconds. Minimum value is 3600000 (one hour). Set to 0 to clear.
`externalDatasetReference`	object	No	External dataset reference configuration.
`defaultPartitionExpirationMs`	string	No	Default partition expiration in milliseconds.
`defaultEncryptionConfiguration`	object	No	Encryption configuration for the dataset.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Patch BigQuery ML Model

GOOGLEBIGQUERY_PATCH_MODEL

Tool to update specific fields in an existing BigQuery ML model using PATCH semantics. Use when you need to modify model metadata like description, friendly name, labels, or expiration time without replacing the entire model resource.

Input parameters

Name	Type	Required	Description
`labels`	object	No	The labels associated with this model. Label keys and values can be no longer than 63 characters, can only contain lowercase letters, numeric characters, underscores and dashes.
`model_id`	string	Yes	Required. Model ID of the model to patch.
`dataset_id`	string	Yes	Required. Dataset ID of the model to patch.
`project_id`	string	Yes	Required. Project ID of the model to patch.
`description`	string	No	Optional. A user-friendly description of this model.
`friendlyName`	string	No	Optional. A descriptive name for this model.
`expirationTime`	string	No	Optional. The time when this model expires, in milliseconds since the epoch. If not present, the model will persist indefinitely.
`encryptionConfiguration`	object	No	Encryption configuration for the model.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Patch BigQuery Table

GOOGLEBIGQUERY_PATCH_TABLE

Tool to update specific fields in an existing BigQuery table using RFC5789 PATCH semantics. Only the fields provided in the request are updated; unspecified fields remain unchanged. Use when you need to modify table metadata like description, friendly name, labels, or expiration time without replacing the entire table resource.

Input parameters

Name	Type	Required	Description
`labels`	object	No	Labels to organize and categorize the table. Keys and values must be lowercase, max 63 characters.
`table_id`	string	Yes	The table ID to update.
`dataset_id`	string	Yes	The dataset ID containing the table to update.
`project_id`	string	Yes	The project ID containing the table to update.
`description`	string	No	User-friendly description of the table.
`friendlyName`	string	No	A descriptive name for the table that appears in the BigQuery UI.
`expirationTime`	string	No	The time when this table expires, in milliseconds since the epoch.
`autodetect_schema`	boolean	No	When true, will autodetect schema; otherwise will keep the original schema.
`requirePartitionFilter`	boolean	No	If true, queries over this table require a partition filter that can be used for partition elimination.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Query

GOOGLEBIGQUERY_QUERY

Query Tool runs a SQL query in BigQuery using the REST API. Use proper BigQuery SQL syntax, e.g., SELECT * FROM \project.dataset.table` WHERE column_name = ‘value’`. Results are returned under data.rows; an empty rows array means no matching data. Large result sets may be returned via remote_file_info instead of inline rows. Verify exact project_id, dataset, table, and column names before running; wrong identifiers trigger invalidQuery or notFound errors.

Input parameters

Name	Type	Required	Description
`query`	string	Yes	Query to run on BigQuery. Use standard SQL syntax.
`location`	string	No	Geographic location where the query should run (e.g., `US`, `EU`, `us-central1`). Defaults to `US` multi-region. Must match the dataset’s actual geographic location; mismatched regions cause query failure.
`project_id`	string	Yes	The project ID to run the query against.
`timeout_ms`	integer	No	Query timeout in milliseconds. Defaults to 10000 (10 seconds).
`max_results`	integer	No	Maximum number of rows to return. If not specified, returns all rows.
`use_legacy_sql`	boolean	No	Whether to use legacy SQL syntax. Defaults to False (standard SQL).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Search All BigQuery Reservation Assignments

GOOGLEBIGQUERY_SEARCH_ALL_ASSIGNMENTS

Tool to search all BigQuery reservation assignments for a specified resource in a particular region. Use when you need to find assignments for a project, folder, or organization. Returns assignments created on the resource or its closest ancestor, covering all JobTypes.

Input parameters

Name	Type	Required	Description
`alt`	string (`"json"` \| `"media"` \| `"proto"`)	No	Data format for response.
`key`	string	No	API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
`query`	string	No	Please specify resource name as assignee in the query. Examples: `assignee=projects/myproject`, `assignee=folders/123`, `assignee=organizations/456`
`xgafv`	string (`"1"` \| `"2"`)	No	V1 error format.
`fields`	string	No	Selector specifying which fields to include in a partial response.
`parent`	string	Yes	Required. The resource name with location (project name could be the wildcard `-`), e.g.: `projects/-/locations/US`.
`callback`	string	No	JSONP
`page_size`	integer	No	The maximum number of items to return per page.
`page_token`	string	No	The next_page_token value returned from a previous List request, if any.
`quota_user`	string	No	Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
`oauth_token`	string	No	OAuth 2.0 token for the current user.
`upload_type`	string	No	Legacy upload protocol for media (e.g. ‘media’, ‘multipart’).
`access_token`	string	No	OAuth access token.
`pretty_print`	boolean	No	Returns response with indentations and line breaks.
`upload_protocol`	string	No	Upload protocol for media (e.g. ‘raw’, ‘multipart’).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Set BigQuery Routine IAM Policy

GOOGLEBIGQUERY_SET_ROUTINE_IAM_POLICY

Tool to set the IAM access control policy for a BigQuery routine resource. Use this to grant or modify access permissions for users, service accounts, or groups. Include the etag from getIamPolicy to prevent concurrent modifications.

Input parameters

Name	Type	Required	Description
`policy`	object	Yes	The IAM policy to set, containing bindings (array of role-members mappings), optional etag and version.
`dataset_id`	string	Yes	Required. Dataset ID of the routine.
`project_id`	string	Yes	Required. Project ID of the routine.
`routine_id`	string	Yes	Required. Routine ID.
`update_mask`	string	No	Field mask for selective policy updates. Specify fields to update (e.g., `bindings,etag`).

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Test BigQuery Routine IAM Permissions

GOOGLEBIGQUERY_TEST_ROUTINE_IAM_PERMISSIONS

Tool to test which IAM permissions the caller has on a BigQuery routine. Returns the subset of requested permissions that the caller actually has. Use to verify access before performing operations.

Input parameters

Name	Type	Required	Description
`dataset_id`	string	Yes	Required. Dataset ID of the routine to test IAM permissions for.
`project_id`	string	Yes	Required. Project ID of the routine to test IAM permissions for.
`routine_id`	string	Yes	Required. Routine ID to test IAM permissions for.
`permissions`	array	Yes	Required. The set of permissions to check for the resource. Array of permission strings like `bigquery.routines.get`, `bigquery.routines.update`, `bigquery.routines.delete`.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Undelete BigQuery Dataset

GOOGLEBIGQUERY_UNDELETE_DATASET

Tool to undelete a BigQuery dataset within the time travel window. If a deletion time is specified, the dataset version deleted at that time is undeleted; otherwise, the most recently deleted version is restored.

Input parameters

Name	Type	Required	Description
`dataset_id`	string	Yes	Required. Dataset ID of the dataset being undeleted.
`project_id`	string	Yes	Required. Project ID of the dataset to be undeleted.
`deletion_time`	string	No	Optional. The exact time when the dataset was deleted (RFC3339 format). If not specified, it will undelete the most recently deleted version.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Update BigQuery Connection

GOOGLEBIGQUERY_UPDATE_CONNECTION

Tool to update a specified BigQuery connection using the BigQuery Connection API. Use when you need to modify connection properties such as friendly name, description, or connection-specific settings. For security reasons, credentials are automatically reset if connection properties are included in the update mask.

Input parameters

Name	Type	Required	Description
`aws`	object	No	Connection properties specific to Amazon Web Services.
`name`	string	Yes	Required. Name of the connection to update in the format `projects/{project_id}/locations/{location_id}/connections/{connection_id}`.
`azure`	object	No	Connection properties specific to Azure.
`spark`	object	No	Connection properties for Apache Spark.
`cloudSql`	object	No	Connection properties specific to Cloud SQL.
`kmsKeyName`	string	No	Optional. The Cloud KMS key that is used for encryption.
`updateMask`	string	Yes	Required. Update mask for the connection fields to be updated. Comma-separated list of field paths (e.g., `friendlyName,description`). For security reasons, credentials are reset if connection properties are in the mask.
`description`	string	No	User provided description.
`cloudSpanner`	object	No	Connection properties specific to Cloud Spanner.
`friendlyName`	string	No	User provided display name for the connection.
`cloudResource`	object	No	Connection properties for delegation of access to GCP resources.
`salesforceDataCloud`	object	No	Connection properties specific to Salesforce DataCloud.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Update BigQuery Dataset

GOOGLEBIGQUERY_UPDATE_DATASET

Tool to update information in an existing BigQuery dataset using the PUT method. The update method replaces the entire dataset resource, whereas the patch method only replaces fields that are provided in the submitted dataset resource. Use when you need to modify dataset properties like description, access controls, or default settings.

Input parameters

Name	Type	Required	Description
`access`	array	No	Optional. An array of objects that define dataset access for one or more entities. If unspecified, BigQuery adds default dataset access for projectReaders, projectWriters, projectOwners, and the dataset creator.
`labels`	object	No	Optional. Labels to organize and categorize the dataset. Labels are key-value pairs. Keys and values must be lowercase, max 63 characters.
`location`	string	Yes	Required. Geographic location where the dataset resides. This cannot be changed after dataset creation. Examples: `US`, `EU`, `us-central1`, `europe-west1`.
`dataset_id`	string	Yes	Required. Dataset ID of the dataset being updated. This is used in the URL path.
`project_id`	string	Yes	Required. Project ID of the dataset being updated. This is used in the URL path.
`description`	string	No	Optional. A user-friendly description of the dataset.
`friendlyName`	string	No	Optional. A descriptive name for the dataset. This is a user-friendly label that appears in the BigQuery UI.
`datasetReference`	object	Yes	Required. Dataset reference containing the dataset ID and project ID. This must match the path parameters.
`defaultCollation`	string	No	Optional. Defines the default collation specification of future tables created in the dataset. Supported values: `und:ci` (undetermined locale, case insensitive) or `''` (empty string for case-sensitive).
`isCaseInsensitive`	boolean	No	Optional. TRUE if the dataset and its table names are case-insensitive, otherwise FALSE. By default, this is FALSE.
`maxTimeTravelHours`	integer	No	Optional. Defines the time travel window in hours. The value can be from 48 to 168 hours (2 to 7 days). The default value is 168 hours if this is not set.
`defaultRoundingMode`	string (`"ROUNDING_MODE_UNSPECIFIED"` \| `"ROUND_HALF_AWAY_FROM_ZERO"` \| `"ROUND_HALF_EVEN"`)	No	Optional. Defines the default rounding mode specification of new tables created within this dataset.
`linkedDatasetSource`	object	No	A dataset source type which refers to another BigQuery dataset.
`storageBillingModel`	string (`"STORAGE_BILLING_MODEL_UNSPECIFIED"` \| `"LOGICAL"` \| `"PHYSICAL"`)	No	Optional. Updates storage_billing_model for the dataset. LOGICAL uses logical bytes, PHYSICAL uses physical bytes.
`defaultTableExpirationMs`	integer	No	Optional. The default lifetime of all tables in the dataset, in milliseconds. The minimum lifetime value is 3600000 milliseconds (one hour). To clear an existing default expiration, set to 0.
`externalDatasetReference`	object	No	Configures the access a dataset defined in an external metadata storage.
`defaultPartitionExpirationMs`	integer	No	Optional. The default partition expiration, expressed in milliseconds.
`defaultEncryptionConfiguration`	object	No	Encryption configuration for the dataset.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Update BigQuery Routine

GOOGLEBIGQUERY_UPDATE_ROUTINE

Tool to update an existing BigQuery routine (function or stored procedure). This replaces the entire routine resource with the provided definition. Use when modifying routine logic, arguments, return types, or other configuration. Ensure all required fields are provided as this is a full replacement operation.

Input parameters

Name	Type	Required	Description
`language`	string	No	The language of the routine. Options: `SQL`, `JAVASCRIPT`, `PYTHON`, `JAVA`, `SCALA`. Defaults to `SQL` if remote_function_options is absent.
`arguments`	array	No	Optional. The list of arguments for the routine.
`dataset_id`	string	Yes	The dataset ID of the routine to update. Used in the URL path.
`project_id`	string	Yes	The project ID of the routine to update. Used in the URL path.
`returnType`	object	No	Data type specification for BigQuery routine arguments and return values.
`routine_id`	string	Yes	The routine ID of the routine to update. Used in the URL path.
`strictMode`	boolean	No	Optional. For procedures, enables additional error checking. Default is TRUE.
`description`	string	No	Optional. A description of the routine.
`routineType`	string	Yes	REQUIRED. The type of routine. Options: `SCALAR_FUNCTION`, `PROCEDURE`, `TABLE_VALUED_FUNCTION`, `AGGREGATE_FUNCTION`.
`securityMode`	string	No	Optional. The security mode of the routine. Options: `DEFINER`, `INVOKER`.
`sparkOptions`	object	No	Options for a user-defined Spark routine.
`definitionBody`	string	Yes	REQUIRED. The body of the routine. For SQL functions, this is the expression (without parentheses). For JavaScript, this is the evaluated string.
`returnTableType`	object	No	Table type returned by table-valued functions.
`determinismLevel`	string	No	Optional. The determinism level of JavaScript UDFs. Options: `DETERMINISTIC`, `NOT_DETERMINISTIC`.
`routineReference`	object	Yes	REQUIRED. The routine reference in the request body. Must match the path parameters.
`importedLibraries`	array	No	Optional. For JavaScript routines, the paths of imported JavaScript libraries.
`dataGovernanceType`	string	No	Optional. If set to `DATA_MASKING`, the function is validated as a masking function.
`remoteFunctionOptions`	object	No	Options for a remote user-defined function.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not

Update BigQuery Table

GOOGLEBIGQUERY_UPDATE_TABLE

Tool to update an existing BigQuery table. The update method replaces the entire Table resource, whereas the patch method only replaces fields that are provided. Use when you need to modify table properties like schema, description, labels, partitioning, or clustering configuration.

Input parameters

Name	Type	Required	Description
`labels`	object	No	Optional. Labels to organize and group your tables. Keys and values must be lowercase, max 63 characters.
`schema`	object	No	Schema of a table.
`table_id`	string	Yes	Required. Table ID of the table to update.
`clustering`	object	No	Configures table clustering.
`dataset_id`	string	Yes	Required. Dataset ID of the table to update.
`project_id`	string	Yes	Required. Project ID of the table to update.
`description`	string	No	Optional. A user-friendly description of this table.
`friendlyName`	string	No	Optional. A descriptive name for this table.
`expirationTime`	string	No	Optional. The time when this table expires, in milliseconds since the epoch.
`tableReference`	object	Yes	Required. Reference identifying the table. Must match the path parameters.
`defaultCollation`	string	No	Optional. Defines the default collation specification of new STRING fields in the table.
`timePartitioning`	object	No	Configures time-based partitioning for the table.
`autodetect_schema`	boolean	No	Optional. When true will autodetect schema, else will keep original schema.
`rangePartitioning`	object	No	Configures range-based partitioning for the table.
`requirePartitionFilter`	boolean	No	Optional. If set to true, queries over this table require a partition filter.
`encryptionConfiguration`	object	No	Encryption configuration for the table.
`externalDataConfiguration`	object	No	Configuration for external data sources.

Output

Name	Type	Required	Description
`data`	string	Yes	Data from the action execution
`error`	string	No	Error if any occurred during the execution of the action
`successful`	boolean	Yes	Whether or not the action execution was successful or not