Create Tool

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)

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.

Configuration for an external API tool. This tool type represents an external API endpoint that the LLM can call.

Configuration for a knowledge base tool. This tool type represents a knowledge base endpoint that the LLM can call.

Configuration for calling a function that already exists in this codebase.

The function is named by function_id, lives under common/workflow_functions/, and must carry the @workflow_function decorator; see common.workflow_functions.registry. Its signature, argument schema and description are derived from the function itself, so unlike an inline-Python tool this config does not have to restate them — signature and args_schema here are optional overrides.

tool_id means a saved tool document, not a registry key. That is the opposite of InbuiltFunctionToolConfig, where the two are the same field, and the difference is deliberate: keeping the function's identity (function_id) apart from the document's (tool_id) is what lets a team save per-team configuration for a function without the two ids ever being confused for one another.