A precise explainer of native tool calling (function calling): what the protocol is, the request/response JSON on the wire, how the model emits it, and why small models fail to produce it.

An LLM only ever outputs text — so how does an AI agent run a tool? The answer is the native tool call, a precise, trained, parseable protocol that most people hand-wave over. Here is exactly what it is, what happens on the wire, and why a small model that knows what to do still cannot make one.

Tag: Function Calling

Tag: Function Calling

What a Native Tool Call Actually Is