check_harness

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the output shape (pass/warn/fail per pillar, plus blocking reasons) and the dependency on 'the skill's latest pipeline run', but says nothing about whether the call is read-only/non-mutating, cost, or what happens when no pipeline run exists.

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?

Three tight sentences: purpose first, return semantics second, call condition last. No filler and nothing repeated from the schema or name.

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, the description correctly compensates by explaining the return values and the meaning of a blocking result, which is what an agent needs to act on the response. It is nearly complete for a one-parameter read tool; only edge-case behavior (skill with no pipeline run, read-only guarantee) is unstated.

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 parameter has 100% schema description coverage ('Skill UUID or slug.'), so the schema does the work and the description adds no further parameter meaning. Baseline 3 is appropriate for a fully documented parameter set.

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 gives a specific verb and resource ('Check whether a skill is cleared to run unattended') and immediately scopes the result ('pass/warn/fail across the four harness pillars'). It is clearly distinguishable from validation/lint siblings by the 'unattended run clearance' framing, though it never names a sibling to disambiguate against skills.flightCheck or skill.reliability.

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?

'Call this before using a skill for a task you will not review' states a concrete triggering condition. There is no explicit exclusion or named alternative, but the when-to-use context is clear enough that an agent knows when the tool applies.

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