CtrlK
BlogDocsLog inGet started
Tessl Logo

tool-design

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.

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/tool-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is comprehensive and well-organized with useful examples and a clear audit checklist, but it is verbose for its token budget and leans on principle-level guidance over executable workflow. Tightening restated concepts and pushing overlapping detail into the references would improve all dimensions.

Suggestions

Collapse the repeated consolidation/tool-as-contract explanations into a single concise statement to improve conciseness.

Add explicit validation/checkpoint steps (e.g., 'audit against the checklist, fix gaps, re-audit') to the Tool Selection Framework and audit sections for workflow_clarity.

Move material duplicated in best_practices.md out of the body, keeping SKILL.md as a lean overview that points to the reference, to strengthen progressive_disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient and well-structured, but the consolidation principle and tool-as-contract framing are restated multiple times and some sections explain concepts Claude already knows; it could be tightened without losing clarity.

2 / 3

Actionability

Provides concrete code examples (the optimize_tool_description function, the get_customer example, MCP naming snippets) and a specific audit checklist, but much of the guidance is principle-level and several examples are illustrative rather than copy-paste executable.

2 / 3

Workflow Clarity

A numbered Tool Selection Framework and an audit checklist provide sequence, but neither includes explicit validation checkpoints or validate-fix-retry feedback loops, so checkpoints remain implicit.

2 / 3

Progressive Disclosure

References are real, one level deep, and signaled with 'Read when' guidance, but the body is fairly monolithic and overlaps significantly with best_practices.md, so content that could be split out remains inline.

2 / 3

Total

8

/

12

Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and well-differentiated with explicit routing guidance. Its main weakness is trigger phrasing that is somewhat technical rather than mirroring natural user requests.

Suggestions

Add concrete user-utterance style triggers (e.g., 'Use when the user asks to design a tool, write or fix a tool description, or consolidate overlapping tools') to improve trigger_term_quality.

Lead with the natural-language 'when to use' clause before the technical 'unit of work' phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as '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', matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what the skill does (the enumerated capabilities) and when to use it ('Use this when the unit of work is a single tool or a set of tools'), plus explicit routing, satisfying both the what and when with explicit triggers.

3 / 3

Trigger Term Quality

Contains relevant terms like 'tool descriptions', 'naming conventions', 'error recovery messages', and 'tool-set consolidation', but the primary trigger ('unit of work is a single tool or a set of tools') is technical/meta phrasing rather than natural user utterances, so common variations are missing.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (tool-interface layer) and explicitly routes adjacent work to project-development and multi-agent-patterns, making conflict with other skills unlikely.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
muratcankoylan/Agent-Skills-for-Context-Engineering
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.