Draft page

This page is an outline. It describes what will be covered and is not yet complete technical documentation.

Function calling lets a model return a structured request to invoke a tool rather than a direct answer. It is the mechanism underneath most agent architectures, and the point where model output starts to have side effects.

That makes both the schema design and the validation of the model’s requests security- relevant, not merely functional.

What you will learn

  • How a function-calling exchange proceeds, turn by turn.
  • How to describe tools so a model uses them correctly.
  • Why every tool call must be validated before execution.
  • How multi-step tool use composes into agent behaviour.

This page is an outline. The subsections below are the planned structure; they are filled in as the handbook is written.

The function-calling loop

Draft

Describing tools to the model

Draft

Handling a tool call request

Draft

Validating arguments before execution

Draft

Multi-step and parallel tool use

Draft

Failure modes

Draft