Tool Design

muratcankoylan/agent-skills-for-context-engineering

This is the skill for designing the tool layer between deterministic code and non-deterministic agents. It covers writing tool descriptions that agents actually route on, designing schemas and error messages, MCP server design, and deciding when to consolidate or split tools. The core principle is consolidation: if you can't definitively say which tool applies in a situation, the agent won't either. The skill pushes toward fewer, more comprehensive tools rather than sprawling catalogs where agents pick wrong half the time. Use it when the unit of work is a single tool or tool set. It explicitly doesn't cover project architecture decisions or whether to use sub-agents, which route to other skills.

skills.sh installs: 291
GitHub stars: 18.3K
last updated: May 26, 2026

View on GitHub

Install

$ npx -y skills add muratcankoylan/agent-skills-for-context-engineering --skill tool-design --agent claude-code

Installs into .claude/skills of the current project.

Files

Tool Design for Agents

Design every tool as a contract between a deterministic system and a non-deterministic agent. Unlike human-facing APIs, agent-facing tools must make the contract unambiguous through the description alone: agents infer intent from descriptions and generate calls that must match expected formats. Every ambiguity becomes a potential failure mode that no amount of prompt engineering can fix.

The unit of work for this skill is a single tool or a tool catalog. Project-shape, pipeline architecture, task-model-fit, and cost-at-the-project-level decisions belong to project-development. Deciding whether to introduce sub-agents belongs to multi-agent-patterns. This skill owns the interface layer that connects deterministic code to the agent.