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

Beyond the readOnlyHint annotation it discloses the tool's deterministic character, the three exact defect classes it detects, the deliberate limits of pixel statistics (confidently wrong on the excluded cases), and that the response includes a fixed visual_checklist the caller must answer by viewing. This is substantially richer than the annotations provide.

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?

Purpose is front-loaded in the first sentence and most sentences carry distinct information (scope, exclusions, interpretation rule). It is on the long side, and the trailing '[#feb72a]' token is stray noise that earns nothing.

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 takes on the burden of describing the return and does so - a fixed visual_checklist to be answered by viewing the render. Combined with the explicit scope boundaries and readOnly/openWorld annotations, an agent has everything needed to call and interpret it.

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?

Only one parameter, preview_url, and schema description coverage is 100%, so the schema fully carries the semantics. The description adds nothing specific about the URL (e.g. accepted formats or whether it must be a platform-hosted render), 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 and resource - a QC gate for a rendered product MOCKUP - and explicitly separates itself from the sibling verify_design_quality ('verify_design_quality checks the design; this checks the render on the garment'). An agent can route between the two without opening either schema.

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?

Explicitly bounds the tool: it catches three named deterministic defects and explicitly does NOT decide upright, clipped, seam-split, or face-count cases, naming the alternative (looking at the image). It also tells the caller how to treat a clean result ('no hard defect found', not 'the mockup is good'), which is real usage guidance, not inference.

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