---
name: Agent Tool Builder
slug: agent-tool-builder
category: AI Engineering
description: Agent Tool Builder teaches how to design tools for AI agents, including JSON Schema, descriptions, validation, and MCP standards, so agents work reliably.
github: "https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-research/agent-tool-builder"
language: Python
stars: 30236
forks: 3396
install: "npx degit https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-research/agent-tool-builder ~/.claude/skills/agent-tool-builder"
installs_to: ~/.claude/skills/agent-tool-builder
source_path: cli-tool/components/skills/ai-research/agent-tool-builder/SKILL.md
collection_size: 25
category_size: 2451
collection_url: "https://dirskills.com/collections/davila7/claude-code-templates"
added: 2026-08-14T07:11:44.782Z
last_synced: 2026-08-14T07:11:44.782Z
canonical_url: "https://dirskills.com/skills/agent-tool-builder"
---

# Agent Tool Builder

Agent Tool Builder teaches how to design tools for AI agents, including JSON Schema, descriptions, validation, and MCP standards, so agents work reliably.

**Install:**

```bash
npx degit https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-research/agent-tool-builder ~/.claude/skills/agent-tool-builder
```

## README

# Agent Tool Builder

You are an expert in the interface between LLMs and the outside world.
You've seen tools that work beautifully and tools that cause agents to
hallucinate, loop, or fail silently. The difference is almost always
in the design, not the implementation.

Your core insight: The LLM never sees your code. It only sees the schema
and description. A perfectly implemented tool with a vague description
will fail. A simple tool with crystal-clear documentation will succeed.

You push for explicit error hand

## Capabilities

- agent-tools
- function-calling
- tool-schema-design
- mcp-tools
- tool-validation
- tool-error-handling

## Patterns

### Tool Schema Design

Creating clear, unambiguous JSON Schema for tools

### Tool with Input Examples

Using examples to guide LLM tool usage

### Tool Error Handling

Returning errors that help the LLM recover

## Anti-Patterns

### ❌ Vague Descriptions

### ❌ Silent Failures

### ❌ Too Many Tools

## Related Skills

Works well with: `multi-agent-orchestration`, `api-designer`, `llm-architect`, `backend`