CtrlK
BlogDocsLog inGet started
Tessl Logo

devtu-optimize-descriptions

Optimize tool descriptions in ToolUniverse JSON configs for clarity and usability. Reviews descriptions for missing prerequisites, unexpanded abbreviations, unclear parameters, and missing usage guidance. Use when reviewing tool descriptions, improving API documentation, or when user asks to check if tools are easy to understand.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is highly actionable with excellent concrete examples, but it is repetitive and monolithic — duplicate checklists and inline material that would benefit from reference files. Validation exists but is not woven into a checkpointed workflow.

Suggestions

Consolidate the 'Quick Optimization Checklist' and 'Description Quality Checklist' into one list, and drop or trim the 'Testing Description Quality' section since it restates the same items as questions.

Move the 'Common Patterns by Tool Type' templates, the full before/after example, and the abbreviation glossary into reference files (e.g. references/patterns.md, references/abbreviations.md) referenced one level deep from SKILL.md.

Reframe the work as a sequenced workflow with an embedded validation checkpoint (apply fixes → run `python3 -m json.tool` → fix and re-validate on failure → proceed) instead of leaving validation as a detached end section.

DimensionReasoningScore

Conciseness

Content is mostly actionable with little concept-explanation padding, but it is verbose: the optimization checklist recurs as a second 'Description Quality Checklist', and the 'Testing Description Quality' section restates those same items as questions.

2 / 3

Actionability

Provides concrete before/after JSON, numbered mutually-exclusive options, specific filter syntax with operators and fields, and runnable validation commands — copy-paste ready guidance for the domain.

3 / 3

Workflow Clarity

Improvements are organized by priority (Critical/High/Medium) and validation commands exist, but validation is a detached end section rather than an integrated fix→validate→retry checkpoint within a sequenced batch-edit workflow, capping clarity at 2.

2 / 3

Progressive Disclosure

The skill is a single ~340-line file with no bundle references; content that could be split out (Common Patterns by Tool Type, the full before/after example, the abbreviation glossary) is inline, matching the level-2 'content that should be separate is inline' anchor.

2 / 3

Total

9

/

12

Passed

Description

100%

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, trigger-rich, and complete with an explicit 'Use when' clause and a distinct ToolUniverse niche. It reads as a strong, third-person skill description with no notable gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete review actions — 'missing prerequisites, unexpanded abbreviations, unclear parameters, and missing usage guidance' — matching the multi-action anchor rather than the single-action level 2.

3 / 3

Completeness

Explicitly answers both what ('Optimize tool descriptions... Reviews descriptions for...') and when via a clear 'Use when...' clause, satisfying the level-3 anchor.

3 / 3

Trigger Term Quality

Natural user phrases are present ('reviewing tool descriptions', 'improving API documentation', 'check if tools are easy to understand'), covering terms a user would actually say; not merely technical jargon.

3 / 3

Distinctiveness Conflict Risk

Scoped to 'ToolUniverse JSON configs' with triggers tied to tool-description review, giving a clear niche unlikely to conflict; written in third person ('Optimize', 'Reviews') with no voice penalty.

3 / 3

Total

12

/

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
mims-harvard/ToolUniverse
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.