Tool Use (Function Calling)
The ability of an AI model to call external functions, APIs, or tools as part of generating a response.
Tool use (also called function calling) is a capability where an LLM, instead of generating only text, can also invoke predefined tools or functions. The model decides when a tool is needed, formats the right parameters, and processes the result before continuing its response.
Examples: a coding assistant runs a terminal command and reads the output, a chatbot queries a database to answer a user's question, or an AI checks the current weather before responding. The AI does not execute the tools directly; it generates structured calls that your application executes and returns results for.
Tool use is the foundation of agentic AI. When an AI can call tools in a loop (decide what to do, call a tool, read the result, decide the next step), it becomes an agent capable of completing complex, multi-step tasks autonomously.