> ## Documentation Index > Fetch the complete documentation index at: https://docs.interactly.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get Tool > Endpoint to retrieve a tool configuration by its ID. Checks both custom tools in the database and inbuilt tools from the registry. ## OpenAPI ````yaml https://api-prod.interactly.ai/api-docs/workflows/api.json get /workflows/v1/tools/{tool_id} openapi: 3.1.0 info: title: Interactly API description: API for building interactly.ai services version: 1.1.0 contact: name: Interactly url: https://interactly.ai email: developers@interactly.ai servers: - url: https://api-prod.interactly.ai description: API Server security: [] paths: /workflows/v1/tools/{tool_id}: get: tags: - Tools summary: Get Tool description: >- Endpoint to retrieve a tool configuration by its ID. Checks both custom tools in the database and inbuilt tools from the registry. operationId: workflow_service_get_tool_v1_tools__tool_id__get parameters: - name: tool_id in: path required: true schema: type: string title: Tool Id responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ToolsResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - bearer: [] components: schemas: ToolsResponse: properties: tool: $ref: '#/components/schemas/ToolsModel' description: Single tool object type: object required: - tool title: ToolsResponse description: |- Response model for a single tool. Contains a ToolsModel object. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ToolsModel: properties: team_id: anyOf: - type: string - type: 'null' description: ID of the team that owns this edge created_by: anyOf: - type: string - type: 'null' description: ID of the user who created this edge updated_by: anyOf: - type: string - type: 'null' description: ID of the user who last updated this edge created_at: type: string format: date-time title: Created At updated_at: type: string format: date-time title: Updated At _id: anyOf: - $ref: '#/components/schemas/PydanticObjectId' - type: 'null' description: MongoDB document ObjectID tool_config: anyOf: - oneOf: - $ref: '#/components/schemas/InlinePythonToolConfig' - $ref: '#/components/schemas/InbuiltFunctionToolConfig' - $ref: '#/components/schemas/ExternalAPIToolConfig' - $ref: '#/components/schemas/KnowledgeBaseToolConfig' discriminator: propertyName: type mapping: external_api: $ref: '#/components/schemas/ExternalAPIToolConfig' inbuilt_function: $ref: '#/components/schemas/InbuiltFunctionToolConfig' inline_python: $ref: '#/components/schemas/InlinePythonToolConfig' knowledge_base: $ref: '#/components/schemas/KnowledgeBaseToolConfig' - type: 'null' title: Tool Config description: Tool Configuration type: object title: ToolsModel description: >- Stores a tool config present in the workflow system. It contains configuration fields for different types of tools (inbuilt_function, inline_python, external_api). ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError PydanticObjectId: type: string maxLength: 24 minLength: 24 pattern: ^[0-9a-f]{24}$ example: 5eb7cf5a86d9755df3a6c593 InlinePythonToolConfig: properties: logical_id: anyOf: - type: string - type: 'null' title: Tool ID description: Unique identifier for the tool input_field_disallowed: true tool_id: anyOf: - type: string - type: 'null' title: Attachable Tool ID description: >- Reference to the tool already created in the Workflow System. If not provided, the tool config is assumed to be provided inline here. input_field_type: inline_python_tool_selection name: anyOf: - type: string - type: 'null' title: Tool Name description: Name for the tool description: anyOf: - type: string - type: 'null' title: Tool Description description: Human friendly description for the tool (not used by AI) category: anyOf: - type: string - type: 'null' title: Tool Category description: Category for the tool. E.g math, ehr, etc signature: anyOf: - type: string - type: 'null' title: Tool Signature description: >- Docstring or signature for the tool used by AI. If provided and there is a default signature already, it will override the default signature. input_field_type: textarea args_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Tool Arguments Schema description: >- Schema for the arguments that the tool accepts. This should be a JSON schema dictionary. Information provided here will override any default arguments schema. static_messages_config: anyOf: - $ref: '#/components/schemas/StaticMessagesConfig' - type: 'null' title: Static Messages Configuration description: >- Static messages that an LLM node should emit while this tool is being invoked result_runtime_variable_name: anyOf: - type: string - type: 'null' title: Result Runtime Variable Name description: Name of the runtime variable to store the result from this tool call default: tool_result ignore_content_received_during_llm_tool_call_specification: type: boolean title: Ignore content received during LLM tool call specification description: >- If true, any free-text content the LLM returns in the same response as a call to this tool is ignored: not emitted via AssistantResponseEvent, not added to chat history, and not added to the node's structured output. When a response contains multiple tool calls, the text is ignored only if every tool call targets a tool for which this flag is set. default: false type: type: string const: inline_python title: Tool Type description: Type of the tool. Must be 'inline_python' default: inline_python input_field_not_visible: true code: anyOf: - type: string - type: 'null' title: Tool Code description: >- Python code to be executed by the tool. It should define a function with proper signature and descriptions for its parameters. input_field_type: textarea type: object title: Inline Python Tool description: >- Configuration for an inline Python tool. The "code" field should contain a self-contained executable Python function. Example value of "code" string could be: def add( a: float, b: float, ) -> float: return float(a + b) InbuiltFunctionToolConfig: properties: logical_id: anyOf: - type: string - type: 'null' title: Tool ID description: Unique identifier for the tool input_field_disallowed: true tool_id: anyOf: - type: string - type: 'null' title: Attachable Tool ID description: >- Reference to the tool already created in the Workflow System. If not provided, the tool config is assumed to be provided inline here. input_field_type: inbuilt_tool_selection name: anyOf: - type: string - type: 'null' title: Tool Name description: Name for the tool description: anyOf: - type: string - type: 'null' title: Tool Description description: Human friendly description for the tool (not used by AI) category: anyOf: - type: string - type: 'null' title: Tool Category description: Category for the tool. E.g math, ehr, etc signature: anyOf: - type: string - type: 'null' title: Tool Signature description: >- Docstring or signature for the tool used by AI. If provided and there is a default signature already, it will override the default signature. input_field_type: textarea args_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Tool Arguments Schema description: >- Schema for the arguments that the tool accepts. This should be a JSON schema dictionary. Information provided here will override any default arguments schema. static_messages_config: anyOf: - $ref: '#/components/schemas/StaticMessagesConfig' - type: 'null' title: Static Messages Configuration description: >- Static messages that an LLM node should emit while this tool is being invoked result_runtime_variable_name: anyOf: - type: string - type: 'null' title: Result Runtime Variable Name description: Name of the runtime variable to store the result from this tool call default: tool_result ignore_content_received_during_llm_tool_call_specification: type: boolean title: Ignore content received during LLM tool call specification description: >- If true, any free-text content the LLM returns in the same response as a call to this tool is ignored: not emitted via AssistantResponseEvent, not added to chat history, and not added to the node's structured output. When a response contains multiple tool calls, the text is ignored only if every tool call targets a tool for which this flag is set. default: false type: type: string const: inbuilt_function title: Tool Type description: Type of the tool. Must be 'inbuilt_function' default: inbuilt_function input_field_not_visible: true configurable_key: anyOf: - type: string - type: 'null' title: Configurable Tool Key description: >- Stable key identifying which configurable inbuilt tool this is (e.g. 'call_forward'). None for plain static inbuilt references. input_field_not_visible: true extra_config: anyOf: - additionalProperties: true type: object - type: 'null' title: Extra Configuration description: >- Tool-specific user configuration values. Schema is defined per configurable key. input_field_not_visible: true type: object title: Inbuilt Function Tool description: >- Configuration for an inbuilt function tool. This tool type refers to functions that are already registered in the tools registry. The "tool_id" field must match the ID (decorated with "@tool_id") of a registered tool. ExternalAPIToolConfig: properties: logical_id: anyOf: - type: string - type: 'null' title: Tool ID description: Unique identifier for the tool input_field_disallowed: true tool_id: anyOf: - type: string - type: 'null' title: Attachable Tool ID description: >- Reference to the tool already created in the Workflow System. If not provided, the tool config is assumed to be provided inline here. input_field_type: external_api_tool_selection name: anyOf: - type: string - type: 'null' title: Tool Name description: Name for the tool description: anyOf: - type: string - type: 'null' title: Tool Description description: Human friendly description for the tool (not used by AI) category: anyOf: - type: string - type: 'null' title: Tool Category description: Category for the tool. E.g math, ehr, etc signature: anyOf: - type: string - type: 'null' title: Tool Signature description: >- Docstring or signature for the tool used by AI. If provided and there is a default signature already, it will override the default signature. input_field_type: textarea args_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Tool Arguments Schema description: >- Schema for the arguments that the tool accepts. This should be a JSON schema dictionary. Information provided here will override any default arguments schema. static_messages_config: anyOf: - $ref: '#/components/schemas/StaticMessagesConfig' - type: 'null' title: Static Messages Configuration description: >- Static messages that an LLM node should emit while this tool is being invoked result_runtime_variable_name: anyOf: - type: string - type: 'null' title: Result Runtime Variable Name description: Name of the runtime variable to store the result from this tool call default: tool_result ignore_content_received_during_llm_tool_call_specification: type: boolean title: Ignore content received during LLM tool call specification description: >- If true, any free-text content the LLM returns in the same response as a call to this tool is ignored: not emitted via AssistantResponseEvent, not added to chat history, and not added to the node's structured output. When a response contains multiple tool calls, the text is ignored only if every tool call targets a tool for which this flag is set. default: false type: type: string const: external_api title: Tool Type description: Type of the tool. Must be 'external_api' default: external_api input_field_not_visible: true api_endpoint: anyOf: - type: string - type: 'null' title: API Endpoint description: The endpoint URL of the external API api_method: anyOf: - $ref: '#/components/schemas/APIMethodType' - type: 'null' title: API Method description: HTTP method to use for the API call (e.g., GET, POST) default: GET api_headers: additionalProperties: type: string type: object title: API Headers description: >- HTTP headers to include with the API request (e.g., authorization, content-type) default: {} api_body: anyOf: - additionalProperties: true type: object - type: string - type: 'null' title: API Request Body description: >- The request body payload for the API call. Usually applicable for POST/PUT methods. input_field_type: textarea type: object title: External API Tool description: >- Configuration for an external API tool. This tool type represents an external API endpoint that the LLM can call. KnowledgeBaseToolConfig: properties: logical_id: anyOf: - type: string - type: 'null' title: Tool ID description: Unique identifier for the tool input_field_disallowed: true tool_id: anyOf: - type: string - type: 'null' title: Attachable Tool ID description: >- Reference to the tool already created in the Workflow System. If not provided, the tool config is assumed to be provided inline here. input_field_type: kb_tool_selection name: anyOf: - type: string - type: 'null' title: Tool Name description: Name for the tool description: anyOf: - type: string - type: 'null' title: Tool Description description: Human friendly description for the tool (not used by AI) category: anyOf: - type: string - type: 'null' title: Tool Category description: Category for the tool. E.g math, ehr, etc default: Knowledge Base signature: anyOf: - type: string - type: 'null' title: Tool Signature description: >- Docstring or signature for the tool used by AI. If provided and there is a default signature already, it will override the default signature. default: >- Searches the knowledge bases given a natural language query and retrieves relevant chunks of information matching the query. input_field_type: textarea args_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Tool Arguments Schema description: >- Schema for the arguments that the tool accepts. This should be a JSON schema dictionary. Information provided here will override any default arguments schema. field_visibility_level: super_admin input_field_not_visible: true static_messages_config: anyOf: - $ref: '#/components/schemas/StaticMessagesConfig' - type: 'null' title: Static Messages Configuration description: >- Static messages that an LLM node should emit while this tool is being invoked result_runtime_variable_name: anyOf: - type: string - type: 'null' title: Result Runtime Variable Name description: Name of the runtime variable to store the result from this tool call default: kb_tool_result ignore_content_received_during_llm_tool_call_specification: type: boolean title: Ignore content received during LLM tool call specification description: >- If true, any free-text content the LLM returns in the same response as a call to this tool is ignored: not emitted via AssistantResponseEvent, not added to chat history, and not added to the node's structured output. When a response contains multiple tool calls, the text is ignored only if every tool call targets a tool for which this flag is set. default: false type: type: string const: knowledge_base title: Tool Type description: Type of the tool. Must be 'knowledge_base' default: knowledge_base input_field_not_visible: true target_knowledge_base_ids: items: type: string type: array title: Target Knowledge Base IDs description: The IDs of the knowledge bases to query input_field_type: knowledge_base_selection type: object title: Knowledge Base Tool description: >- Configuration for a knowledge base tool. This tool type represents a knowledge base endpoint that the LLM can call. StaticMessagesConfig: properties: static_messages: items: type: string type: array title: Static Messages description: List of pre-configured messages from which one will be emitted static_messages_selection_mode: anyOf: - $ref: '#/components/schemas/SelectionMode' - type: 'null' title: Static Messages Selection Mode description: Selection mode for static messages default: random type: object title: StaticMessagesConfig APIMethodType: type: string enum: - GET - POST - PUT - DELETE title: APIMethodType description: Enumeration of HTTP methods for API calls. SelectionMode: type: string enum: - random - sequence title: SelectionMode securitySchemes: bearer: scheme: bearer bearerFormat: Bearer type: http description: >- Retrieve your API Key from [Dashboard API Keys Section](https://dashboard.interactly.ai/api-keys). ````