Diff two skins

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

Annotations already declare readOnlyHint, idempotentHint, and closed-world scope, so safety is covered. The description adds genuine value beyond that by describing the return artifact (changed-pixel mask over the texture map) and the magenta encoding for changed regions.

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 compact sentences, front-loaded with the core action and ending with the return convention. Nothing is wasted, though the return-value sentence partially overlaps with the existing output schema.

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 a full output schema, rich annotations, and fully documented parameters, the description only needs to frame intent and it does so. A brief note on what inputs are accepted (JSON object vs. text) would close the small remaining gap.

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 100% and both before/after parameters are fully documented in the schema, including the skinspec.v1 format reference. The description adds no additional parameter-level guidance, so the baseline 3 applies.

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 (compare/diff) and resource (two skin specs) plus the output granularity (per-face, pixel by pixel). This clearly distinguishes it from write-oriented siblings like texel_patch or rendering siblings like texel_render.

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?

"Use it to confirm a patch touched only what you intended" gives a concrete scenario, implicitly positioning it after texel_patch. It does not, however, name an alternative tool or state any when-not-to-use condition.

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