agent-tool-design

Automate LLM agent tool design with naming, schemas, and error handling.

Updated Feb 21, 2026
One-click install
npx skills add https://github.com/abzhaw/juliaz_agents --skill agent-tool-design
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-tool-design
Source: https://github.com/abzhaw/juliaz_agents/tree/main/.agent/skills/agent-tool-design
Command: npx skills add https://github.com/abzhaw/juliaz_agents --skill agent-tool-design

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Designing tools for LLM agents often suffers from inconsistent naming, unclear input schemas, and weak error handling, leading to brittle integrations across MCP bridges, cowork-mcp, and orchestrator layers.

Core Features & Use Cases

  • One tool, one responsibility: keep actions isolated and easy to reason about.
  • Descriptive names and rich descriptions: enable the LLM to select the correct tool with confidence.
  • Explicit error semantics: always return useful errors and support safe retries.
  • Idempotent by default: design tools that can be retried without side effects.
  • MCP Tool Schema guidance: provide a clear template for input, outputs, and annotations to standardize tool definitions.

Quick Start

Define a new MCP tool by specifying its title, input schema, and idempotency, then implement and wire it to the backend.

Frequently Asked Questions about agent-tool-design

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design MCP tools for LLM agents with consistent naming and error handling?

Designing MCP tools for LLM agents requires enforcing naming conventions, clear input schemas, and robust error handling to ensure safe, traceable operations across bridging and orchestrator layers.

What is the best way to make LLM agent tools idempotent for safe retries?

Making LLM agent tools idempotent involves designing operations that can be retried without side effects, utilizing explicit error semantics and structured input schemas to return useful errors safely.

How does explicit error semantics improve LLM tool integrations?

Explicit error semantics improve LLM tool integrations by ensuring tools always return useful errors, enabling the LLM to select correct tools confidently and supporting safe retries across MCP integrations.

Can I use this tool design workflow across cowork-mcp and orchestrator layers?

Yes, this tool design workflow applies across bridging, cowork-mcp, and orchestrator layers, enabling consistent tool definitions, traceable descriptions, and safe operations within your MCP integrations.

Do I need structured frontmatter in SKILL.md for tool discovery?

Yes, structured frontmatter in SKILL.md is required for discovery, while optional assets, scripts, and references provide extended guidance for standardizing tool definitions and input schemas.

Why should LLM agent tools follow the one tool one responsibility principle?

Following the one tool one responsibility principle keeps actions isolated and easy to reason about, enabling the LLM to select the correct tool confidently based on descriptive names and rich descriptions.