---
title: "Tool use and function calling best practices"
slug: "tool-use-and-function-calling"
category: "ai-agents"
tags: ["ai-agents", "tool-use", "function-calling", "structured-output", "best-practices"]
status: "stable"
last_updated: 2026-06-07
summary: "How to define, describe, and guard tools so an LLM calls them correctly: clear schemas, named arguments, validation, error feedback, and a minimal tool surface."
description: "Tool use and function calling: write clear tool schemas, name and type every argument, validate inputs, return useful errors, and keep the tool surface minimal."
aliases: ["function calling best practices", "LLM tool use", "designing tools for agents", "tool calling patterns"]
related: ["[[ai-agents/agent-architecture-patterns]]", "[[ai-agents/reliable-agents-in-production]]", "[[ai-agents/structured-output]]", "[[ai-agents/mcp-tool-design]]", "[[ai-agents/prompt-injection-defense]]", "[[glossary/function-calling]]", "[[glossary/tool-call]]", "[[glossary/tool-result]]", "[[prompt-engineering/output-constraints]]"]
---

## Overview

Tool use, also called function calling, lets an LLM invoke external functions by emitting a structured call that your code executes and returns. Reliable tool use is a schema-design problem: the model calls the right tool with valid arguments when the tool is named, typed, and described well, and fails when it is not. This page covers the provider-agnostic rules; for the Model Context Protocol specifics see [[ai-agents/mcp-tool-design]], and for the loop that consumes tool results see [[ai-agents/agent-architecture-patterns]].

## Define one clear job per tool

Each tool should do one thing a name can describe. `search_orders` beats a `do_stuff` tool with a mode flag. A focused tool is easier for the model to select correctly and easier for you to validate. Overlapping tools cause the model to pick the wrong one; keep the set small and distinct.

## Write the description for the model, not the docs

The tool description is a prompt. State what the tool does, when to use it, when not to, and what it returns, in plain language. Name units and formats in the description, not just the schema. A good description prevents the most common failure: the model calling a valid tool at the wrong time. See [[ai-agents/mcp-tool-design]].

## Type every argument and constrain the schema

Declare each parameter with a JSON Schema type, mark required fields, use enums for closed sets, and add format hints (`date`, `email`). Constrained schemas shrink the space of malformed calls. This is the same discipline as [[ai-agents/structured-output]] and [[prompt-engineering/output-constraints]].

## Validate inputs before executing

Never trust the arguments the model emits. Validate against the schema, then against business rules, before the call touches a system. A model can hallucinate an ID or an out-of-range value. Validation is also the first line of defense when tool arguments are derived from untrusted text; see [[ai-agents/prompt-injection-defense]].

## Return errors the model can act on

When a call fails, return a structured error that says what went wrong and how to fix it, not a stack trace. "order_id not found; call search_orders first" lets the model recover; "Error 500" makes it retry blindly. Useful [[glossary/tool-result]] errors turn a dead end into a self-correction.

## Keep the tool surface minimal and safe

Expose the fewest tools that solve the task. Gate destructive actions behind confirmation, sandbox side effects, and rate-limit per session. Every tool is attack surface and failure surface; see [[ai-agents/reliable-agents-in-production]].

## Pitfalls

- Vague tool names and descriptions; the model guesses and calls the wrong one.
- Free-text arguments where an enum would do; constrain the inputs.
- Trusting model-emitted arguments without validation.
- Returning raw exceptions instead of actionable [[glossary/tool-result]] errors. See [[glossary/function-calling]] and [[glossary/tool-call]] for the underlying mechanics.

## Related

- [[ai-agents/agent-architecture-patterns]]
- [[ai-agents/reliable-agents-in-production]]
- [[ai-agents/structured-output]]
- [[ai-agents/mcp-tool-design]]
- [[ai-agents/prompt-injection-defense]]
- [[glossary/function-calling]]
- [[glossary/tool-call]]