Read timestamped subtitles from a Bilibili video part, distinguish human from platform AI captions, and return coverage plus a truncation cursor; errors clearly when subtitles are unavailable.
读取一个分 P 的带时间戳字幕，区分人工和平台 AI 字幕。返回覆盖范围与截断游标；没有字幕时明确报错。本版不提供 ASR。
| Name | Required | Description | Default |
|---|---|---|---|
| part | No | ||
| limit | No | ||
| video | Yes | ||
| end_seconds | No | ||
| start_seconds | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive behavior, yet the description still adds real context: output carries a coverage range and a truncation cursor, subtitle type (human vs AI) is surfaced, and missing subtitles produce an explicit error. Missing is any statement about auth or rate limits, though openWorldHint signals external dependence.
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?
Four short clauses, each carrying distinct information: scope, subtitle typing, return shape, error behavior, and exclusion of ASR. The most important constraint (one part, subtitles) comes first with no filler.
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?
Return behavior and error behavior are explained even though there is no output schema, which is good. But with five parameters at zero schema coverage, an agent cannot tell what 'video' accepts or how start_seconds/end_seconds interact with the returned coverage range, so the definition is not complete enough for correct invocation.
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 5 parameters, and the description documents none of them. '分P' hints at part and '截断游标' hints at limit, but video format, start_seconds/end_seconds ranges, and the 200/500 limits are left entirely unstated — the largest gap in this definition.
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 states a specific verb and resource: it reads the timestamped subtitles of one part (分P) and distinguishes human from platform-AI subtitles. That is precise enough to separate it from bilibili_get_video, but no sibling is named, so the differentiation is only implied by scope.
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 negative scope sentence '本版不提供 ASR' tells the agent what this tool will not do, which is useful routing information. However, it never says when to call this instead of bilibili_get_video or how to react to a no-subtitle error beyond 'it errors clearly'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.