skills.checks

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose useful traits: the checks are deterministic (not LLM-judged) and the result is a categorical pass/warn/fail rather than a numeric score. It omits whether the check is read-only, whether it touches the filesystem or network, and what the heuristics actually inspect.

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?

Two short, front-loaded sentences with no filler; the outcome semantics are stated immediately. The unexplained internal codename 'scanner h5' adds a token of jargon without turning it into information.

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?

With no output schema and no annotations, the description does cover the return shape at a high level (pass/warn/fail with findings), which is the most important missing structured data. It still leaves parameter meaning, usage routing, and side-effect profile unaddressed, so it is only minimally complete.

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 single 'path' parameter has 0% schema description coverage, so the description must compensate. 'A local skill' hints that path points at a local skill, but it never clarifies directory vs file, absolute vs relative, or whether a skill root or a manifest is expected.

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?

States a specific verb and resource ('Check a local skill') plus the method ('deterministic heuristics, scanner h5') and the outcome type ('pass / warn / fail with findings'). It does not differentiate itself from close siblings such as skills.lint, skills.validateFormat or skills.flightCheck, so an agent must guess which checker applies.

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?

No when-to-use, when-not-to-use, or alternative is offered. The word 'local' is the only routing signal, implicitly contrasting with cloud tools, but nothing tells the agent why to pick this over the many other skill-checking siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.