What is tool use or function calling in LLMs, and how do you design good tools for an agent?

The short answer

Function calling lets an LLM output a structured request to invoke an external function with arguments, which the runtime executes and feeds back, enabling agents to act in the world. Good tool design uses clear names and descriptions, minimal well-typed parameters, narrow single-purpose scope, least privilege, and informative error messages so the model can choose and call them reliably.

How to think about it

Function calling lets an LLM output a structured request to invoke an external function with arguments, which the runtime executes and feeds back, enabling agents to act in the world. Good tool design uses clear names and descriptions, minimal well-typed parameters, narrow single-purpose scope, least privilege, and informative error messages so the model can choose and call them reliably.

Learn it properly What agentic AI means

Keep practising

How do function/tool calling and LLM agents work at a high level? What is an AI agent, and how does it differ from a single LLM call? What prompt engineering techniques should every LLM practitioner know? When should you use prompt engineering versus fine-tuning to adapt an LLM? What techniques reduce LLM cost and latency in production?

All NLP & LLMs questions

Explore further

Function/tool calling AGENTS.md, Skills & Tools FunctionAgent & ReActAgent Tools — defining, calling, validating

ReAct Agent LlamaIndex Prompt Engineering