review_frames

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

With no annotations, the description must carry the burden. It discloses that the tool is free ('免费'), that it produces 'findings.action' for fixes, and that it serves as a pre-video gate. However, it never explicitly states whether the tool is read-only or if it modifies any state. The verb '审查' (review) and the instruction to fix per findings imply it is diagnostic, but this is not made explicit. It adds useful context but leaves the mutation question ambiguous.

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?

The description is dense but front-loaded: it starts with the core purpose and specific checks, then adds the critical gating instruction before generate_videos, and closes with the fix/re-review workflow. Every sentence adds value, though the emoji-laden formatting and rapid-fire phrasing make it slightly cluttered. It is appropriately sized for the amount of context it conveys.

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?

Given the single parameter, no output schema, and no annotations, the description covers the essential points: what it reviews, when to run it, why it matters, and what to do with the output (follow findings.action). It hints at the return structure ('findings.action') but does not detail the full output format. For a review tool with this simple interface, this is largely complete, leaving only minor gaps.

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?

The schema only defines episode_id as an integer >0 with no description (schema coverage 0%). The tool description never mentions episode_id or explains how it relates to the review targets (e.g., that it identifies the episode whose frame layer is being reviewed). Although an agent could infer from the tool name and context, the description adds no semantic meaning beyond the schema. With zero coverage, the description should compensate, but it does not.

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 '审查镜头图片层' (review shot image layer) and enumerates specific checks: character identity anchor coverage, image generation failure rate, orphan character variants, and scene contamination. This clearly distinguishes it from sibling review tools like review_script and review_storyboards, which target different pipeline stages. The purpose is unambiguous and specific.

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?

The description explicitly states '★generate_videos 之前必须先跑本工具' (must run before generate_videos), providing a concrete trigger and explaining why (video generation is the most expensive step, and drifted first frames are the most typical junk output). It also instructs to apply fixes according to findings.action and then re-review, giving a full usage loop. This is strong, actionable guidance.

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