scan_intra_shot_cuts

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

With no annotations provided, the description carries the full behavioral burden. It reveals the tool is free ('免费零扣费'), lists return fields, explains interpretation ('成片观感切点 = 镜与镜的接缝 + 这里报的镜内跳切'), discloses empirical engine incidence rates (WAN 11/12, Seedance 1/6, H3 0/5), and notes that negative prompts cannot block the artifact.

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 long but well-structured, using star markers and paragraph breaks to separate trigger, output, interpretation, and remediation. Each section adds meaningful context, though the dense statistics and minor redundancy ('免费零扣费' restated) could be tightened.

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?

For a complex detection tool with no output schema, the description thoroughly covers return values, interpretation guidance, engine_suspect semantics, exclusions, and follow-up action. The only small ambiguity is the reference to 'detail' without listing it among the returned fields, but the agent still has enough to call and act on the tool.

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 has one required parameter, episode_id, but schema coverage is 0% and the description never mentions this parameter or how it should be populated. The only indirect clue is '本剧引擎', which implies an episode context. Given the low coverage, the description was expected to compensate but 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 explicitly defines the tool's purpose: detecting intra-shot hard cuts ('望远镜特写→高空全景→人物中景') that are invisible in the storyboard and timeline and can only be found by scanning the picture. It uses a specific verb-resource pair and clearly distinguishes this from general editing-rhythm problems.

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?

It gives a concrete trigger condition: run this first when a customer reports '镜头切太快 / 一个镜头里画面跳来跳去'. It also states when not to use other fixes ('重新拆镜或改转场都没用') and recommends the alternative regenerate_shot_video when engine_suspect=true, plus explains the automatic exclusion of group-mode and montage shots.

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