---
title: "What is tool calling?"
excerpt: "Letting an LLM invoke functions you define — search, queries, actions. It's how models reach past their training data, and how they cause real side effects."
definition: "Tool calling (or function calling) is the mechanism by which an LLM emits a structured request to invoke a function you defined, receives the result, and continues reasoning — letting the model take actions and fetch live data."
date: "2026-07-09"
lastModified: "2026-07-09"
author: "Teo Deleanu"
authorAvatar: "/team/teo.jpg"
tags: ["Agents", "AI Engineering", "Tool Calling"]
keywords:
  - "what is tool calling"
  - "llm function calling explained"
  - "how tool calling works"
---

Tool calling is how a language model does something other than produce text. You describe a set of functions — their names, parameters, and purpose — and the model, when it decides a tool is needed, emits a structured call. Your code runs it and returns the result, which the model reads and continues from. It is the foundation every [AI agent](/glossary/ai-agent) is built on.

## Why it matters in production

This is how a model reaches past its frozen training data: to query your database, search your docs, or take an action in the world. It is also where side effects live. A tool that deletes records is one confidently-wrong model decision away from a bad day, so tool design is a safety surface, not just a feature.

## The common mistake

Dumping your entire API surface into the tool list. The model has to choose the right tool from the descriptions you wrote, and a bloated, overlapping, or vaguely-described catalog produces wrong calls — the model picks `updateUser` when it meant `getUser`. Tool selection quality is mostly a function of how sharply you wrote the tool descriptions.

## How we actually use it

We treat the tool catalog as a designed product: few tools, sharp descriptions, parameters the model can fill unambiguously. We wrote the discipline up in [context engineering the tool catalog](/blog/context-engineering-tool-catalog), and when the tools need to live behind a standard interface, we expose them via the [Model Context Protocol](/glossary/model-context-protocol) — see [inside an MCP tool server](/blog/inside-an-mcp-tool-server). Guardrails on destructive tools are covered under [guardrails](/glossary/guardrails).