Equip LLMs with callable functions — code executors, web search, APIs — and design schemas that make tool selection reliable.
Five passes over the same idea, each from a different angle. Do them in order, or jump to whichever you need.
Tool use (function calling) is the superpower that turns a language model into an agent that can act on the world. The model sees tool schemas and decides which to invoke. Great tool design means clear names, precise descriptions, and narrow parameter schemas. Poorly designed tools cause the model to hallucinate arguments or call the wrong function.
