Hugging Face

Overview

Hugging Face is the leading open source machine learning platform where teams build, train, and deploy language models, vision models, datasets, and AI applications. With the integration in SquadOS, your agents can run inference via OpenAI-compatible chat completion, generate text embeddings, search and explore models and datasets from the Hub, create repositories, manage discussions, and track the latest scientific papers from the AI community.

• Official website: https://huggingface.co/
• Composio documentation: docs.composio.dev/toolkits/hugging_face

Authentication

This tool uses API key (API_KEY) or OAuth 2.0 (OAUTH2) to connect.

You will need the following fields:

Field	Required	Description
api_key	Yes	Hugging Face User Access Token, obtained from Settings → Access Tokens in your account.

How to get credentials

1. Go to huggingface.co and log in (or create an account).
2. Click your avatar in the top-right corner and go to Settings.
3. In the side menu, click Access Tokens.
4. Click New token, choose a descriptive name, and select the Write scope (required to create repositories and commits) or Read (read-only).
5. Click Generate token and copy the displayed value — this is your api_key.

Tip

Use tokens with the minimum required scope. For read-only operations (search, public inference), a Read-scoped token is sufficient and more secure.

How to connect in SquadOS

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

Available actions

Note

This integration exposes 135 actions in total. The most relevant ones are listed below; see the full list in the Composio documentation.

Generate chat completion

HUGGING_FACE_GENERATE_CHAT_COMPLETION

Tool to generate a response given a list of messages in a conversational context. Supports both conversational Language Models (LLMs) and Vision-Language Models (VLMs). Compatible with OpenAI SDK.

Input parameters

Name	Type	Required	Description
model	string	Yes	The model ID to use for chat completion. Format: namespace/model or namespace/model:provider. Examples: meta-llama/Llama-3.2-3B-Instruct, Qwen/Qwen2.5-7B-Instruct-1M.
messages	array	Yes	A list of messages comprising the conversation so far. Each message has a role (system, user, assistant, tool) and content.
temperature	number	No	Sampling temperature between 0 and 2. Higher values like 0.8 make output more random, lower values like 0.2 make it more focused and deterministic.
max_tokens	integer	No	The maximum number of tokens that can be generated. If not specified, the model generates until a natural stopping point.
stream	boolean	No	Whether to stream the response as Server-Sent Events. If true, tokens are returned as they are generated.
tools	array	No	A list of tools the model may call. Currently, only functions are supported.
top_p	number	No	Nucleus sampling parameter. The model considers tokens comprising the top_p probability mass.
response_format	string	No	Response format: text (default), json_object for JSON mode, or json_schema for structured output.
seed	integer	No	Random seed for deterministic sampling.
stop	array	No	Up to 4 sequences where the API will stop generating further tokens.

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.

Generate text embeddings

HUGGING_FACE_GENERATE_EMBEDDINGS

Tool to convert text into vector embeddings for feature extraction, semantic search, and similarity tasks. Use when you need numerical representations of text for ML applications.

Input parameters

Name	Type	Required	Description
inputs	array	Yes	Array of text strings to convert into embeddings. Each string will be processed and returned as a numerical vector representation.
model	string	No	The Hugging Face model ID to use for generating embeddings. Must be a valid embedding model from the Hugging Face model hub.

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.

Create repository

HUGGING_FACE_CREATE_REPO

Tool to create a new repository (model, dataset, or Space) on Hugging Face Hub. Use when you need to initialize a new repository for uploading models, datasets, or deploying Spaces applications.

Input parameters

Name	Type	Required	Description
name	string	Yes	The name of the repository to create. This will be the repository identifier within the namespace.
type	string	No	The type of repository to create: model, dataset, or space. Defaults to model.
private	boolean	No	Whether the repository should be private. If not specified, follows the default visibility setting.
organization	string	No	The organization namespace to create the repository under. If not provided, the repository will be created under your personal namespace.
sdk	string	No	SDK options for Spaces: gradio, streamlit, docker, or static.

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.

Get model information

HUGGING_FACE_GET_MODEL_INFO

Tool to retrieve detailed information about a Hugging Face model repository. Use when you need comprehensive metadata including downloads, likes, tags, configuration, files, and more.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The repository name of the model. For example, bert-base-uncased in google-bert/bert-base-uncased.
namespace	string	Yes	The namespace (organization or user) that owns the model repository. For example, google-bert in google-bert/bert-base-uncased.

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.

List datasets

HUGGING_FACE_LIST_DATASETS

Tool to list datasets on the Hugging Face Hub. Use when you need to discover or search for datasets. Supports filtering by author, search query, tags, and sorting by various properties.

Input parameters

Name	Type	Required	Description
search	string	No	Filter based on substrings for dataset names and their usernames. Use this to search for datasets by keyword.
author	string	No	Filter datasets by an author or organization.
filter	string	No	Filter based on tags. Use this to find datasets with specific tags like task types, languages, or licenses.
sort	string	No	Sorting property: lastModified, trending, likes, or downloads.
limit	integer	No	Limit the number of datasets returned. Defaults to 100.
cursor	string	No	Pagination cursor for fetching the next page of results.
direction	string	No	Sort direction: asc or desc.

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.

Search dataset

HUGGING_FACE_SEARCH_DATASET

Tool to search text in a dataset split on Hugging Face. Searches in columns of type string, even if values are nested in a dictionary. Use when you need to find specific text or patterns within a dataset’s content.

Input parameters

Name	Type	Required	Description
dataset	string	Yes	Name of the dataset to search. Use format owner/dataset-name for user datasets or just dataset-name for official datasets.
config	string	Yes	Name of the configuration/subset of the dataset to search.
split	string	Yes	Name of the dataset split to search.
query	string	Yes	Text to search for in the dataset. Searches in all columns of type string, even if values are nested in a dictionary.
length	integer	No	Length of the slice (number of rows to return). Maximum value is 100.
offset	integer	No	Offset of the slice for pagination. Defaults to 0.

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.

Get dataset first rows

HUGGING_FACE_GET_DATASET_FIRST_ROWS

Tool to get the first 100 rows of a dataset split along with column data types and features. Use when you need to preview or sample dataset content.

Input parameters

Name	Type	Required	Description
dataset	string	Yes	Name of the dataset in format namespace/name. For example, cornell-movie-review-data/rotten_tomatoes or squad.
config	string	Yes	Name of the dataset configuration/subset. Use default for datasets without configurations.
split	string	Yes	Name of the dataset split to retrieve rows from.

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.

Get dataset info

HUGGING_FACE_GET_DATASET_INFO

Tool to get general information about a dataset including description, citation, homepage, license, and features (column schemas). Use when you need to understand dataset structure, available splits, and metadata before working with the data.

Input parameters

Name	Type	Required	Description
dataset	string	Yes	Name of the dataset to retrieve information for. Format: namespace/repo-name (e.g., rajpurkar/squad, ibm/duorc).
config	string	No	Name of the config/subset to retrieve information for. If not provided, returns info for the default 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.

Filter dataset rows

HUGGING_FACE_FILTER_DATASET_ROWS

Tool to filter rows from a dataset on Hugging Face based on specified criteria. Use when you need to retrieve specific rows from a dataset based on column conditions.

Input parameters

Name	Type	Required	Description
where	string	Yes	Filter condition as SQL expression (e.g., column = 'value').
split	string	Yes	Name of the dataset split.
config	string	Yes	Name of the dataset configuration/subset.
dataset	string	Yes	Name of the dataset in format namespace/name.
length	integer	No	Maximum number of rows to return.
offset	integer	No	Number of rows to skip for pagination.
orderby	string	No	Column to order results by.

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.

Get Space info

HUGGING_FACE_GET_SPACE_INFO

Tool to retrieve detailed information about a Hugging Face Space repository. Use when you need metadata, SDK type, hardware configuration, runtime status, or other information about a specific Space.

Input parameters

Name	Type	Required	Description
repo_id	string	Yes	Space repository ID in the format author/space-name (e.g., Qwen/Qwen3-TTS, stabilityai/stable-diffusion).
revision	string	No	Git revision (branch, tag, or commit SHA) to retrieve information for. If not specified, defaults to the main branch.

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.

List Spaces on Hugging Face Hub

HUGGING_FACE_LIST_SPACES

Tool to list Spaces on the Hugging Face Hub with filtering options. Use when you need to discover or search for ML demo applications hosted on Hugging Face.

Input parameters

Name	Type	Required	Description
search	string	No	Filter based on substrings for repos and their usernames.
author	string	No	Filter spaces by a specific author or organization name.
filter	string	No	Filter based on tags (e.g., gradio, streamlit).
sort	string	No	Property to use when sorting results: lastModified, likes, trending, or created.
limit	integer	No	Maximum number of spaces to return. Must be between 1 and 500.
direction	string	No	Direction to sort results: 1 for ascending or -1 for descending.

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.

List inference endpoints

HUGGING_FACE_LIST_ENDPOINTS

Tool to list Hugging Face Inference Endpoints for a specific user or organization. Use when you need to retrieve endpoints, optionally filtered by tags or name.

Input parameters

Name	Type	Required	Description
namespace	string	Yes	User or organization name to list endpoints for.
search	string	No	Filter endpoints by name substring.
tags	string	No	Filter endpoints by tags (comma-separated).
limit	integer	No	Maximum number of endpoints to return per page. Defaults to 20.
cursor	string	No	Pagination cursor to fetch the next or previous 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.

Search papers

HUGGING_FACE_SEARCH_PAPERS

Tool to perform hybrid semantic/full-text search on papers in Hugging Face. Use when you need to find research papers by keywords, topics, or authors.

Input parameters

Name	Type	Required	Description
q	string	No	Search query string to find relevant papers. Use keywords, paper titles, or topics. Supports hybrid semantic and full-text search.
limit	integer	No	Maximum number of papers to return. If not specified, the API will use its default limit.

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.

Get daily papers

HUGGING_FACE_GET_DAILY_PAPERS

Tool to retrieve daily papers from Hugging Face. Use when you need to fetch the latest AI/ML research papers shared on Hugging Face.

Input parameters

Name	Type	Required	Description
date	string	No	Filter papers by specific date (YYYY-MM-DD format).
sort	string	No	Sort option for daily papers: publishedAt or trending.
limit	integer	No	Maximum number of papers to return per page. Defaults to 50.
month	string	No	Filter papers by specific month (YYYY-MM format).
submitter	string	No	Filter papers by submitter username.
p	integer	No	Page number for pagination (0-indexed). Defaults to 0.

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.

Search documentation

HUGGING_FACE_SEARCH_DOCS

Tool to search Hugging Face documentation across all products and libraries. Use when you need to find information about HF tools, models, datasets, or API usage.

Input parameters

Name	Type	Required	Description
q	string	Yes	Search query string to find relevant documentation pages. Use keywords related to the topic you want to learn about.
limit	integer	No	Maximum number of search results to return. Defaults to 10.
offset	integer	No	Number of results to skip for pagination.
product	string	No	Hugging Face product to filter documentation search (e.g., hub, transformers, diffusers, datasets, gradio).

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.

Get trending repositories

HUGGING_FACE_GET_TRENDING

Tool to retrieve trending repositories from Hugging Face. Use when you need to discover popular models, datasets, or spaces that are currently trending on the platform.

Input parameters

Name	Type	Required	Description
type	string	No	Repository type filter: all, dataset, model, or space.
limit	integer	No	Maximum number of trending repositories to return. Defaults to 10.

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.

Get authenticated user info

HUGGING_FACE_GET_WHOAMI

Tool to get information about the authenticated Hugging Face user including username, email, organizations, and token details. Use when you need to identify the current user from an access token or retrieve user profile information.

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.

Create discussion

HUGGING_FACE_CREATE_DISCUSSIONS

Tool to create a new discussion on a Hugging Face repository (model, dataset, or Space). Use when you need to start a conversation, report an issue, or create a pull request discussion.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The name of the repository where the discussion will be created.
namespace	string	Yes	The namespace (username or organization) that owns the repository.
repo_type	string	Yes	The type of repository: models, spaces, or datasets.
title	string	Yes	The title of the discussion. Must be between 3 and 200 characters.
description	string	Yes	The description/content of the discussion. Can contain markdown formatting. Maximum 65536 characters.
pull_request	boolean	No	Whether this discussion should be created as a pull request.

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.

Create discussion comment

HUGGING_FACE_CREATE_DISCUSSIONS_COMMENT

Tool to create a new comment on a Hugging Face repository discussion. Use when you need to add comments or replies to discussions on models, datasets, or spaces.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The repository name where the discussion exists. For example, gpt2 or my-dataset.
namespace	string	Yes	The namespace (username or organization) that owns the repository.
repo_type	string	Yes	The type of repository: models, spaces, or datasets.
num	string	Yes	The discussion number or ID to comment on.
comment	string	Yes	The comment text to post on the discussion. Must be between 1 and 65536 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.

Change discussion status

HUGGING_FACE_CHANGE_DISCUSSIONS_STATUS

Tool to change the status of a Hugging Face repository discussion. Use when you need to open or close discussions on models, datasets, or spaces.

Input parameters

Name	Type	Required	Description
num	string	Yes	The discussion number or ID to change the status of.
repo	string	Yes	The repository name where the discussion exists. For example, bert-base-uncased or my-dataset.
namespace	string	Yes	The namespace (username or organization) that owns the repository.
repo_type	string	Yes	The type of repository: models, spaces, or datasets.
status	string	Yes	The new status: open to reopen or closed to close.
comment	string	No	Optional comment to add when changing the status.

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.

List discussions

HUGGING_FACE_LIST_DISCUSSIONS

Tool to list all discussions from a Hugging Face repository. Use when you need to retrieve open, closed, or pull request discussions from a model, dataset, or Space.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The repository name.
namespace	string	Yes	The namespace (username or organization) that owns the repository.
repo_type	string	Yes	The type of repository: models, spaces, or datasets.
status	string	No	Filter by discussion status: open, closed, or all.
type	string	No	Filter by type: discussion or pull_request.
p	integer	No	Page number for pagination (0-indexed).

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.

Create collection

HUGGING_FACE_CREATE_COLLECTION

Tool to create a new collection on Hugging Face. Use when you need to organize and curate models, datasets, spaces, papers, or other collections into a named collection.

Input parameters

Name	Type	Required	Description
namespace	string	Yes	The namespace (username or organization) under which to create the collection.
title	string	Yes	The title of the collection. Must be between 1 and 60 characters.
description	string	No	Optional description for the collection. Maximum 150 characters.
private	boolean	No	If not provided, the collection will be public.
item	object	No	Item to be added to the collection upon creation.

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.

List collections

HUGGING_FACE_LIST_COLLECTIONS

Tool to list collections on the Hugging Face Hub. Use when you need to discover collections of models, datasets, spaces, or papers. Collections are curated groups of repositories organized by users.

Input parameters

Name	Type	Required	Description
owner	string	No	Filter collections by owner username or organization.
item	string	No	Filter collections containing a specific item (format: type/namespace/repo).
sort	string	No	Sorting criteria for collections.
limit	integer	No	Maximum number of collections to return.

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.

List repository files

HUGGING_FACE_LIST_REPO_TREE

Tool to list files and directories in a Hugging Face Hub repository. Use when you need to explore the structure of a model, dataset, or Space repository.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The repository name.
namespace	string	Yes	The namespace (username or organization) that owns the repository.
repo_type	string	Yes	The type of repository: models, spaces, or datasets.
path	string	No	Specific path within the repository to list. If omitted, lists the root.
rev	string	No	Git revision (branch, tag, or commit hash). Defaults to the main branch.
recursive	boolean	No	Whether to list files recursively in subdirectories.

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.

Create dataset commit

HUGGING_FACE_CREATE_DATASETS_COMMIT

Tool to create a commit in a Hugging Face dataset repository. Use when you need to add, update, or delete files in a dataset. Supports both regular files and Large File Storage (LFS) for large binary files.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The name of the dataset repository.
namespace	string	Yes	The namespace (username or organization) that owns the dataset.
branch	string	Yes	The branch where the commit will be created.
commit_message	string	Yes	The commit message (maximum 500 characters).
operations	array	Yes	List of file operations to perform. Each operation specifies the file path and content.
create_pr	boolean	No	Whether to create a pull request instead of committing directly.

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.

Create model commit

HUGGING_FACE_CREATE_MODELS_COMMIT

Tool to create a commit in a Hugging Face model repository. Use when you need to add, update, or delete model files. Supports LFS for large files such as model weights.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The name of the model repository.
namespace	string	Yes	The namespace (username or organization) that owns the model.
branch	string	Yes	The branch where the commit will be created.
commit_message	string	Yes	The commit message (maximum 500 characters).
operations	array	Yes	List of file operations to perform.
create_pr	boolean	No	Whether to create a pull request instead of committing directly.

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.

Create Space commit

HUGGING_FACE_CREATE_SPACES_COMMIT

Tool to create a commit in a Hugging Face Space repository. Use when you need to add, update, or delete Space files. Optionally supports creating a pull request instead of a direct commit.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The name of the Space repository.
namespace	string	Yes	The namespace (username or organization) that owns the Space.
branch	string	Yes	The branch where the commit will be created.
commit_message	string	Yes	The commit message (maximum 500 characters).
operations	array	Yes	List of file operations to perform.
create_pr	boolean	No	Whether to create a pull request instead of committing directly.

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.

List notifications

HUGGING_FACE_LIST_NOTIFICATIONS

Tool to list notifications for the authenticated Hugging Face user. Use when you need to monitor activity on followed repositories, discussions, and pull requests.

Input parameters

Name	Type	Required	Description
type	string	No	Filter by notification type.
status	string	No	Filter by notification status: read or unread.
p	integer	No	Page number for pagination (0-indexed).
limit	integer	No	Maximum number of notifications to return.

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.

Create or update Space secret

HUGGING_FACE_CREATE_OR_UPDATE_SPACE_SECRET

Tool to create or update a secret in a Hugging Face Space. Use when you need to manage sensitive environment variables such as API keys and tokens used by the Space.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The name of the Space repository.
namespace	string	Yes	The namespace (username or organization) that owns the Space.
key	string	Yes	The name of the secret (key).
value	string	Yes	The value of the secret.
description	string	No	Optional description for the secret.

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.

Request repository access

HUGGING_FACE_REQUEST_ACCESS

Tool to send an access request for a gated repository on Hugging Face. Use when you need to request access to restricted models or datasets.

Input parameters

Name	Type	Required	Description
repo	string	Yes	The name of the repository to request access to.
namespace	string	Yes	The namespace (username or organization) that owns the repository.
repo_type	string	Yes	The type of repository: models, datasets, or spaces.

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.