What a re-import changed

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

readOnlyHint=true already tells the agent this is a non-mutating read, so the description's remaining job is to add context, and it does by listing the classes of breakage it detects. It stays silent on cost/runtime (diffing a whole project plus skeleton), precedence when both a snapshot and a before file are supplied, and whether the comparison is deep or structural only.

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?

One dense sentence with a front-loaded verb-resource pairing and no filler; the colon-introduced lists pack the diff categories efficiently. It is compact but slightly over-packed, and the animation-playback clause trails after the structural breakdown rather than being foregrounded.

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 5-parameter, no-output-schema comparison tool, the description omits three parameters entirely (including the only required one), does not clarify snapshot-vs-before precedence, and gives no sense of result shape or size. It conveys the concept well but is not complete enough for confident invocation.

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 only 20% (just the 'before' param), so the description must carry the burden, and it explains only two of the five: snapshot (default latest) and before (another .spine/.json). The required 'project' param, plus 'skeleton' and 'fps', are never mentioned in the description and have no schema descriptions, leaving the agent to guess their meaning and whether fps affects the playback comparison.

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 names a specific verb (compares) and concrete resources (a project, a snapshot, another .spine/.json file), and enumerates what the diff surfaces (lost keys, weights, meshes, removed items, animation playback differences). That is far more specific than a tautology and implicitly separates it from spine_compare_animations, but no sibling is named outright, so full distinguishability is left to inference.

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?

It gives a default behavior (snapshot defaults to latest) and a comparison target alternative, which implies the intended workflow after a re-import. It does not state when to reach for this instead of spine_validate, spine_doctor, or spine_compare_animations, nor any prerequisites, so usage is implied rather than directed.

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