---
title: "Tools: Concepts"
description: "Tool selection strategy, safety boundaries, and reliability rules for agentic execution."
icon: "wrench"
mode: "wide"
---

## When to use tools

- Agents need external data or side effects.
- Deterministic systems must be integrated into agent workflows.

## Tool safety rules

- define clear input schemas
- validate outputs before downstream use
- isolate privileged tools behind policy checks

## Canonical links

- Reference: [/en/ai/tools/reference](/en/ai/tools/reference)
- Patterns: [/en/ai/tools/patterns](/en/ai/tools/patterns)
- Troubleshooting: [/en/ai/tools/troubleshooting](/en/ai/tools/troubleshooting)
- Examples: [/en/ai/tools/examples](/en/ai/tools/examples)
- Existing docs: [/en/concepts/tools](/en/concepts/tools)