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

Annotations already declare readOnlyHint=true, destructiveHint=false and a closed world, so safety is covered. The description adds real behavioral context beyond that: the check list, the conditional 'brand' group activated by a brand kit, and the non-obvious side effect that frames=true returns rendered frames alongside each problem.

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 clause, followed by a dense colon list where each item is a distinct check rather than filler. It reads as one long run-on sentence, but no sentence could be cut without losing a concrete detection capability.

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 is the only source of return-value information, and it only discloses the frames payload. The shape of the review report itself — problem list, grouping, severity, whether issues are ordered by timecode — is left unstated for a tool whose entire output is that 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?

At 67% schema coverage the schema already documents platform defaults and projectId's fallback to the open project. The description adds meaning only for frames=true (a rendered frame per problem) and echoes the safe-area platform names, leaving projectId and the 'all' enum value to 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?

States a specific verb and resource ('Review the cut for mistakes') and then enumerates the exact defect classes it detects (black frames, flash frames, safe-area text, caption speed, ducking, loudness). This is clearly a pre-publish QA pass, distinguishable from check_copy (copy review alone) and render_frame (single frame render) without opening any 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?

'before showing it' gives a clear timing/context cue for invocation, and 'With a brand kit it also reviews the brand' explains the conditional scope expansion. It stops short of naming alternatives or exclusions, notably that check_copy exists for standalone copy review and that frames=true overlaps with render_frame, so the agent must infer routing itself.

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