Fetch Bilibili episode subtitles (CC/AI) and return language, timestamped segments, and full text. Errors if no subtitle track exists, prompting audio transcription as fallback.
取单集字幕正文（B 站已有 CC/AI 字幕时）。返回语言、分段(含时间戳)与全文。 没有字幕轨时报错——此时用 download_audio + asr_transcribe 现场转写。
| Name | Required | Description | Default |
|---|---|---|---|
| p | No | ||
| lang | No | zh-CN | |
| url_or_bvid | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses the return structure and the important error behavior: it errors when no subtitle track exists, and suggests the fallback. It does not explicitly state read-only semantics or auth/rate-limit behavior, but 'get' plus the described return/error profile makes the behavior reasonably transparent.
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?
Two tight sentences: the first states what the tool returns, the second states the error condition and the fallback path. No filler, and the core purpose is front-loaded.
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?
The description covers purpose, output, error behavior, and fallback, which is strong for a getter. However, with no output schema, no annotations, and 0% schema description coverage, leaving 'p' and 'lang' unexplained is a real gap, so the description is not fully complete 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 coverage is 0%, so the description must compensate. It does not explain what 'p' means (e.g., episode/part index) or what values 'lang' accepts. '单集' and '返回语言' weakly hint at p and lang, but the description adds little concrete parameter meaning beyond the schema's names and defaults.
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 uses a specific verb and resource — '取单集字幕正文' (get single-episode subtitle text) — and states the exact return contents: language, segments with timestamps, and full text. It also clearly distinguishes itself from download_audio/asr_transcribe and batch_download_subtitles.
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 explicitly says to use this tool when Bilibili already has CC/AI subtitles, and gives the alternative for the no-subtitle case: use download_audio + asr_transcribe. This is direct when-to-use and when-not-to-use guidance with named alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.