Validate skeleton

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

Annotations only declare readOnlyHint=true, so the description carries the behavioral load and does add real context: it reveals that validation samples every animation in spine-core and explains the import quirk ('Spine drops them on import') that motivates the missing-reference check. It does not disclose cost/performance of sampling all animations, whether findings are warnings vs errors, or how results are surfaced, which keeps it short of a 5.

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?

Nearly every clause carries a distinct check, so there is little outright waste, but the whole thing is one run-on sentence stitched together with semicolons and an abrupt 'face:' pivot. It is information-dense but poorly structured and hard to scan, which undercuts the front-loading benefit.

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?

For a read-only validator with 6 parameters, a nested face config, and no output schema, the description should say what callers get back (issue list, severities, exit status). It thoroughly covers what is inspected but not the result shape or how to interpret findings, leaving a meaningful gap for a tool whose entire value is its report.

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?

Schema description coverage is 67%, so the baseline is 3 and the description needs to add meaning. It does partially: the face paragraph explains what the face audit compares (blinks vs pose changes, mouth swaps, lash visibility while shut), and the loop-seam check maps to loopAnimations. But the top-level parameters input, runtime and skeleton get no explanatory value, and the face sub-option semantics (hide, lids, mouths, closedFrom) are not clarified beyond the schema.

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 opens with a concrete verb and resource ('Finds problems' in a skeleton) and then enumerates the exact defect classes checked (duplicate names, bone order, missing references, mesh indices, curves, physics keys) plus an animation sampling pass and a face audit. That is far more specific than the title 'Validate skeleton'. It loses a point because it never distinguishes itself from the many overlapping sibling validators (spine_doctor, spine_audit, spine_rig_qa, spine_mix_check, spine_unity_check), so an agent cannot tell which of them to pick.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no mention of alternatives. With five or more sibling tools that plausibly also validate assets, the absence of any routing statement is a real gap. The list of checks only implicitly signals that this is the pre-flight correctness check for a Spine skeleton.

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