Agents & tools
Tool use
Definition
Tool use is a model invoking external capabilities — search, code execution, database queries, APIs — to do things it cannot do from parameters alone, such as fetching current data or performing exact arithmetic.
Tools address the structural limits of a language model. Models cannot know today's data, cannot reliably perform precise arithmetic, and cannot affect the world. Tools supply all three.
The pattern is always the same: the model emits a structured request, your code executes it, and the result returns to the conversation. The model never executes anything directly, which is where your validation boundary belongs.
Tool descriptions are effectively prompts and deserve the same care. Models select tools based on their descriptions, so ambiguous descriptions cause wrong selections — a very common source of agent failure.
Related terms
Function calling
Function calling lets a model request that your code run a specific function with specific arguments. You expose tool definitions; the model returns a structured call, your code executes it, and the result goes back into the conversation.
AI agent
An AI agent is a system where a model plans and takes actions through tools in a loop, rather than producing a single response. It decides what to do next, does it, observes the result, and continues until the goal is met.
MCP (Model Context Protocol)
MCP is an open standard for connecting AI models to external tools and data sources. It replaces bespoke per-integration code with one protocol any compatible client can use.
ReAct pattern
ReAct (Reason + Act) is the core agent loop: the model reasons about what to do, takes an action via a tool, observes the result, then reasons again. It repeats until it can answer.
Guardrails
Guardrails are the constraints that keep an AI system inside acceptable behaviour — input validation, output filtering, topic restrictions, action limits and human approval gates.
Human in the loop
Human in the loop means inserting a person at decision points in an automated workflow — typically to approve consequential actions or review low-confidence outputs before they take effect.
Put this into practice
Understanding the term is step one. Our free courses and tools let you actually use it.