Tool Use (Function Calling)

Tool use (also called function calling) is when you describe a set of tools to the model — each with a name, description, and JSON-schema'd arguments — and the model returns a structured request to call one of them. Your code executes the call and feeds the result back.

This is the foundation of every modern AI agent. The patterns that work: keep tool descriptions short and unambiguous, use enums for fixed choices, and validate the model's output against the schema (it will occasionally invent fields). When tools fail, return a clear error string the model can reason about rather than throwing.