A capability that allows LLMs to invoke external functions, APIs, or services during a conversation. The model decides when to call a tool, formulates the input, and incorporates the tool's output into its response.
Tool calling (also called function calling) enables LLMs to take actions beyond generating text. A Claude model with tool calling enabled can: search the web, query a database, call a payment API, send an email, or run code — by generating a structured tool call that the application executes.
How it works: (1) You define tools with name, description, and parameter schema. (2) The LLM decides when a tool is needed and generates a valid call. (3) Your code executes the tool and returns results. (4) The LLM incorporates results into its response. This is the foundational mechanism behind all AI agents.
Anthropic's AI assistant with industry-leading reasoning and safety
OpenAI's AI assistant powering 100M+ users worldwide
Open-source framework for building production LLM applications
Weekly AI tool reviews, news digests, and how-to guides.
Join 12,000+ builders