Tools And Tool Calling

Integrator defines a tool function with no type hints and a one-line docstring, then wonders why the model passes wrong-typed arguments.

Decorate with @tool and provide type hints + a clear docstring; LangChain derives the tool name, description, and args schema from them. The description is what the model uses to route, so it must describe purpose and arguments precisely.

The model returns two tool_calls in one AIMessage; the integrator returns a single merged ToolMessage without matching tool_call_id.

For each AIMessage.tool_calls entry, execute the tool and return one ToolMessage whose tool_call_id matches the call's id. The next model turn requires every tool_call to have a matching ToolMessage; mismatched or missing ids break the conversation contract.

A tool needs constrained inputs (an enum and a positive int) but the integrator relies on the docstring alone to communicate the constraints.

Define an explicit Pydantic args_schema (via StructuredTool.from_function or @tool with args_schema) so constraints (enums, ranges, required fields) are encoded in the schema sent to the model AND validated before execution. Reject invalid args, do not coerce silently.