Tool call
A request from an AI model to run one action, such as a search or a file write, which the surrounding program carries out.
Tool use (also called function calling) lets Claude call functions that you define or that Anthropic provides.
Anthropic's page says Claude "determines when to call a tool based on the user's request and the tool's description. It then returns a structured call that your application runs (client tools) or that Anthropic runs (server tools)."
The model chooses a tool call; a hook fires whether or not it chose to. Each tool call shows up as a step in a trace.
Pages that use this term
- Failure kind
- How unattended coding agents fail
- Wrong tool use
- Two small changes that stop an agent waiting on you
- How to watch an AI agent and keep an audit trail
- Can you stop an AI agent being tricked?
- Do AI agents actually work? What four benchmarks and one analyst forecast measured between 2024 and 2026
- How do the top AI agent harnesses handle heartbeats?
- How do the top AI agent harnesses handle hooks?
- How do the top AI agent harnesses handle tool calls?
- What the n8n AI Agent node is and what it costs
- How to start with the OpenAI Agents SDK
- How do you stop an AI agent?
- Which AI agent harnesses lead right now?
- Are Zapier and Make AI agents?
- How I Built (and Killed) an AI Startup