# AI Tool Use The capability of [[Large Language Models (LLMs)]] to invoke external tools, APIs, and functions during generation. Instead of producing text, the model outputs a structured tool call (function name + arguments). The harness executes it, and the result is fed back into the model's context for further reasoning. This is the bridge between language understanding and real-world action. Without tool use, LLMs are limited to what they can express in text. With it, they can query databases, call APIs, manipulate files, run code, and interact with any system that exposes an interface. Tool use is the core enabler of [[AI Agents]]. An agent loop is essentially: reason, pick a tool, call it, observe the result, repeat. The quality of tool selection and argument construction depends heavily on the model's understanding of available tools, which is why [[AI Agent Skills]] and [[Harness Engineering]] matter so much. Standardized through protocols like [[Model Context Protocol (MCP)]], which provides a uniform way for models to discover and invoke tools across different providers and runtimes. ## References - ## Related - [[Large Language Models (LLMs)]] - [[AI Agents]] - [[AI Agent Skills]] - [[Model Context Protocol (MCP)]] - [[Harness Engineering]]