Definition: LLM capability to invoke external tools like web search, code execution, file operations, and APIs during a conversation.
— Source: NERVICO, Product Development Consultancy
What is Tool Use
Tool use is the capability of a Large Language Model (LLM) to invoke external tools during a conversation. These tools include web search, code execution, file operations, API calls, and database access. With tool use, a language model transitions from a purely generative system to an agent capable of interacting with the real world.
How it works
When an LLM receives a request that requires external information or a specific action, it generates a structured call to a predefined tool. The system executes that tool, obtains the result, and returns it to the model so it can continue the conversation with updated data. This cycle can repeat multiple times within a single interaction, enabling complex reasoning chains. The model autonomously decides which tools to use, in what order, and with what parameters, based on the conversation context.
Why it matters
Tool use is the foundational capability that transforms a conversational LLM into a functional AI agent. Without it, models are limited to generating text based solely on their training data. With tool use, they can query real-time data, execute operations, and produce verifiable results. For organizations integrating AI into their workflows, tool use determines the difference between a basic chatbot and a system that genuinely automates tasks.
Practical example
A development team configures an agent with tool use to manage incidents. When a developer describes a bug, the agent searches the code repository for affected functions, runs the relevant unit tests, queries internal documentation, and proposes a fix with the full context of the problem. All of this happens within a single conversation, without the developer needing to switch between tools.
Related terms
- Function Calling - The technical mechanism underlying tool use
- MCP Protocol - Open standard for connecting agents to external tools
- LLM - Language models that enable tool use
Last updated: February 2026 Category: Artificial Intelligence Related to: Function Calling, MCP Protocol, AI Agents, LLM Keywords: tool use, llm tools, function calling, ai agents, agentic ai, external tools