# Tool Calling (Function Calling)

> Tool calling, also called function calling, is a language model capability in which the model responds with a structured request to run a specific function, with arguments, instead of plain text. The application runs the function, such as looking up an order or creating a ticket, and returns the result to the model. Tool calling is how AI agents take actions in other systems.

## Why it matters for your business

Tool calling is the bridge between an AI model and your business systems, so it is where much of the value and much of the risk sit. The model only proposes a call; your code decides whether to run it. That means permissions, input validation and approval steps can be enforced in software rather than left to the prompt. Well-designed tools are narrow and clearly described, such as get_invoice_status rather than run_any_sql_query. Poorly scoped tools are a common source of agent errors and security problems.

## Example

A support agent for an online retailer has three tools: look up an order by number, check shipment tracking, and create a return label for orders under 30 days old. When a customer asks where a package is, the model calls the order and tracking tools, then answers. The return tool checks the 30-day rule in code, so the model cannot override it.

Related terms: https://www.lumeor.studio/glossary/ai-agent/, https://www.lumeor.studio/glossary/structured-outputs/, https://www.lumeor.studio/glossary/mcp-model-context-protocol/, https://www.lumeor.studio/glossary/guardrails/, https://www.lumeor.studio/glossary/api-application-programming-interface/

---

Source: https://www.lumeor.studio/glossary/tool-calling/