Agents & tools
Function Calling
A feature that lets an AI model trigger specific functions or APIs in your app instead of just returning text.
01 ——
In plain English
Function calling (also called tool use) lets you tell an AI model about functions it can invoke — for example, get_weather(city) or search_database(query). When the model decides it needs that information, it outputs a structured request for your code to execute, then uses the result in its reply.
Example flow:
- User asks: "What's the weather in Tokyo?"
- Model outputs:
{ "function": "get_weather", "args": { "city": "Tokyo" } } - Your code calls the real weather API
- Model receives the result and writes a natural language response
This is how AI assistants do anything beyond text — searching the web, reading calendars, updating databases, or controlling software.
02 ——
Related terms
Tool Use
The ability of an AI model to call external tools — like a calculator, search engine, or API — to help answer a question.
Agent
An AI system that can take actions, use tools, and make decisions autonomously to complete a goal.
MCP
Model Context Protocol — an open standard that lets AI models connect to external tools and data sources in a consistent way.
API
An interface that lets developers send requests to an AI model and get responses programmatically — the way most AI tools talk to LLMs.
Back to glossaryLast reviewed May 2026