提交单片段视频

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

Annotations already declare non-read-only, open-world, idempotent and non-destructive, and the description adds substantive context beyond that: credit consumption, an authorization prerequisite, required pre-flight verification of model/duration/keyframes, and a conservative resubmission policy keyed to UNKNOWN and terminal state. What it does not clarify is the relationship between that policy and operation_id, which is the actual idempotency key.

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?

It is short and front-loads the cost/authorization warning, and each semicolon clause carries information. But the telegraphic, jargon-dense phrasing (e.g. '只调用已核single_frame视频合同') makes it hard to parse in one pass, and verification rules are interleaved with parameter notes rather than grouped.

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 an output schema covering return values and annotations covering the safety profile, the description sensibly focuses on preconditions and mutation rules. However, for an 11-parameter, 9-required credit-spending mutation, leaving operation_id and expected_sha256 semantics entirely unaddressed is a meaningful 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% across 11 parameters, so the description must carry the load and only partly does: it names model, resolution, a style selector and expected_ratio, plus the caveat that ratio is checked against the project rather than sent as a field. It never explains project_id, episode_id, segment_id, expected_sha256 or operation_id, and its 'style_id或custom_style_prompt' wording does not match the single 'style' object in the schema, which risks mis-parameterization.

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 implies a credit-consuming generation submit ('消耗额度', 'single_frame视频合同', '保存唯一真实新task_id') but never states plainly that it submits an async segment-video job and that the returned task_id is what you poll. The verbose verification clauses crowd out a crisp verb+resource statement, so purpose is inferable rather than stated.

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 real preconditions and exclusions: user must have authorized model parameters and cost, the segment_video model and segment total duration plus selected keyframes must be verified, and 'Pavo生图' must not be called. It also sets resubmission rules ('UNKNOWN禁止重投'; regeneration requires regenerate and a verified terminal old task). It stops short of naming sibling tools such as pavo_script_get_segment_video_task for polling.

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