tool-design
An agent skill by muratcankoylan, from muratcankoylan/Agent-Skills-for-Context-Engineering. Tags: api, automation, debugging, developer-tools, strategy.
What it does
This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats, naming conventions, actionable error recovery messages, MCP server design, tool-set consolidation, and deciding when to add or remove an individual tool. Use this when the unit of work is a single tool or a set of tools. Route project-shape, pipeline architecture, and task-model-fit decisions to project-development; route deciding whether to introduce sub-agents to multi-agent-patterns.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill tool-designOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering
cp -r Agent-Skills-for-Context-Engineering/skills/tool-design ~/.claude/skills/tool-designSafety box score
Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a documentation-and-utility package for designing agent tool interfaces, plus one local Python helper that generates and evaluates tool descriptions. It does not touch networks, secrets, privileged settings, or files outside the repo; the only real runtime surface is the demo-capable script in `scripts/description_generator.py`.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | `scripts/description_generator.py` is runnable Python with a `if __name__ == "__main__":` demo block that builds a schema, renders a description, evaluates it, and prints output; it does not invoke shell commands or other external executables. |
| Network access | 0 (none) | No file performs downloads, API calls, or remote uploads; the Python helper only imports standard-library modules and prints locally generated text. |
| Filesystem reach | 0 (none) | The shipped files are markdown docs and one script; there is no code that reads, writes, or deletes paths outside the repository or working directory. |
| Secrets & credentials | 0 (none) | Nothing references tokens, keys, passwords, `.env` files, keychains, or browser sessions, and the helper does not prompt for credentials. |
| Privilege & persistence | 0 (none) | There is no sudo usage, service registration, global install step, or shell/OS configuration change in the provided files. |
| Instruction hijack surface | 0 (none) | The text is about tool-description quality and does not instruct the agent to ignore policies, skip confirmations, hide actions, or follow remote instructions. |
| Irreversible actions | 0 (none) | The skill only helps author and evaluate tool descriptions; it does not send messages, deploy, delete, pay, book, or otherwise act on the user's behalf. |
| Transparency | 0 (none) | All shipped content is plain text/source; there are no binaries, base64 blobs, generated installers, or uninspectable runtime code paths. |
Before installing
- Read `scripts/description_generator.py` to confirm the only executable behavior is local description generation and the demo `__main__` block.
- Check whether any downstream agent setup imports this helper into production workflows, or whether it remains an offline authoring aid.
- Verify the `references/*.md` files are treated as static documentation, not fetched or executed at runtime.
Rated 2026-10-19 by an automated review of 4 files from the skill's repository.
Source
- Repository
- muratcankoylan/Agent-Skills-for-Context-Engineering (all skills from this repository)
- Path
- skills/tool-design/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- bdi-mental-states — This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations.
- context-degradation — This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion.
- context-engineering-collection — A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems.
- harness-engineering — This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs.
- memory-systems — This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity.
- reasoning-trace-optimizer — Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures.