review_script

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

No annotations are provided, so the description carries the full burden. It discloses that the tool is free ('免费'), acts as a hard gate, does not itself edit the script (fixes go through edit_rewritten_script), and produces findings plus a review_token. It stops short of explicitly stating read-only or side-effect semantics, hence not a 5.

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 a single dense run-on sentence padded with promotional framing ('第①道硬闸·免费'), a warning about downstream magnification, and client-handling instructions. Useful facts are present and front-loaded, but the structure is cluttered and could be organized into concise bullets.

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 low complexity (one parameter, no output schema), the description is largely sufficient: it states review criteria, mandatory position in the pipeline, the fix-and-rereview loop, and the review_token handoff. It does not specify the exact response shape or what to do with the token beyond 'proceed,' leaving a small 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 0% and the description never explains the episode_id parameter itself. The context implies the episode whose rewritten script is being reviewed ('整集重来'), but the parameter meaning and expected value format are left to inference rather than explicitly compensated.

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?

Describes a specific verb+resource: '审查 AI 改写稿' (review AI-rewritten script), and lists concrete review criteria: dialogue line length, emotional turn completeness, opening hook, ending suspense. It differentiates from sibling review tools by targeting the rewritten script stage and naming downstream dependencies (extract_assets, generate_storyboards).

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 states when to use: must run before extract_assets and generate_storyboards, with the reasoning that downstream assets derive from the rewritten script. It also prescribes the workflow: surface findings, fix via edit_rewritten_script, re-review, then proceed with review_token.

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