Technical

What is Tool Use?

An AI model's ability to call external functions, APIs, or services during reasoning.

Definition

Tool use (also called tool calling or function calling) is the capability of an AI model to invoke external tools — APIs, functions, databases, search engines — during its reasoning process. Rather than relying solely on training data, a tool-using model can retrieve current information, take actions, and interact with external systems. Tool use is what transforms an LLM from a text generator into an AI agent.

Example

An AI asked 'what's the current stock price of Apple?' without tool use: gives a stale or hallucinated answer. With tool use: calls a `get_stock_price(ticker: 'AAPL')` function and returns the live price. The same model, dramatically different reliability.

Tool Use vs function-calling: What's the difference?

Tool Use

An AI model's ability to call external functions, APIs, or services during reasoning.

function-calling

Tool use and function calling describe the same capability — different providers use different terminology. OpenAI calls it function calling; Anthropic calls it tool use.

Related terms

Back to glossary