Fully validate a Claude SKILL.md file — frontmatter rules, body quality, security scan, tool collision check. Returns score (0–100), gate (pass/review/fail), and structured errors/warnings.
| Name | Required | Description | Default |
|---|---|---|---|
| tools | No | Optional override tool list if not declared in frontmatter | |
| skill_md | Yes | Full contents of the SKILL.md file including --- frontmatter --- | |
| allowed_tools | No | Optional whitelist; non-listed tools will produce errors |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly describes what the tool does and what it returns (score, gate, structured errors/warnings), which is transparent. It does not disclose scoring thresholds or potential side effects, but validation is inherently read-only, so this is a minor gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence leading with 'Fully validate' and then enumerating the checks and outputs. There is no redundancy or extraneous information, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there is no output schema, the description does a good job of explaining what the tool returns (score, gate, errors/warnings) and what it validates. It could be more complete by explaining the gate logic or noting that the tool does not modify the file, but overall it provides sufficient context for a validation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides 100% description coverage for all three parameters (skill_md, tools, allowed_tools), so the description does not need to add parameter-specific detail. The description adds context about the tool's overall purpose but does not enhance understanding of individual parameters beyond what the schema provides, matching the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to fully validate a SKILL.md file, and specifies the exact checks it performs (frontmatter rules, body quality, security scan, tool collision) as well as the return format (score, gate, errors/warnings). This distinguishes it from sibling tools like lint_frontmatter or scan_security, which focus on isolated aspects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this is the comprehensive validation tool ('Fully validate') while siblings handle specific checks, giving clear context on when to use it. However, it does not explicitly state when not to use it or mention alternatives, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are distinct, but score_skill and validate_skill both run full validation and return score/gate, creating overlap. Descriptions help by distinguishing minimal CI/CD payload from detailed structured errors, but the boundaries are not instantly clear.
All tool names follow a consistent verb_noun snake_case pattern: lint_frontmatter, scan_security, score_skill, validate_skill. This is highly predictable and easy to reason about.
Four tools is an appropriate size for a validation server, covering specific checks and a full validation without bloat or thinness.
The server covers frontmatter linting, security scanning, scoring, and full validation including tool collision checks. No obvious missing operations for the stated purpose of validating Claude Skills.