Search Bilibili and YouTube for song candidates with title, duration, play count, and link, helping you select a full track (1.5–8 min) to use with sing_cover.
在线搜歌（B站优先，YouTube 兜底），返回候选的标题/时长/播放量/链接(含上传者)。挑版本时优先选播放量高、时长 1.5~8 分钟的整曲；标着「切片/片段/翻唱/live」的往往是几十秒的短视频，拿去翻唱会直接踩到副歌中间。不确定是哪一版时，先用它挑一首再调 sing_cover。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 返回几条，默认 5 | |
| query | Yes | 歌名，可带歌手（如「恋爱循环 花泽香菜」） |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and mostly succeeds: it discloses the fallback behavior between two sources, the shape of returned candidates, and a genuine operational trap (short clips that start mid-chorus). It does not state failure behavior when nothing is found, latency, or any limits, though these are minor for a read-only search.
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?
Core capability and source strategy are front-loaded in the first clause, followed by return fields and selection advice. The clip warning is slightly verbose but earns its place by preventing a real failure mode; only minor tightening is possible.
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 2-parameter search with no output schema and no annotations, the description covers what is returned, how to choose among candidates, and what to do next. It omits empty-result behavior and any hint about sing_probe, which keeps it from a 5.
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 100%, so both query and limit are already documented in the schema. The description adds no format or constraint detail beyond the schema's own example, so the baseline of 3 applies.
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?
Uses a concrete verb+resource (在线搜歌) and immediately narrows the scope with its source strategy (B站优先, YouTube 兜底) and the exact fields returned (标题/时长/播放量/链接/上传者). An agent knows exactly what it gets back and can distinguish it from sing_cover, which is positioned as the downstream step.
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 routes the agent: when unsure which version, call this first, then call sing_cover. It also supplies concrete selection heuristics (prefer high view count, 1.5–8 minute full tracks; avoid 切片/片段/翻唱/live clips). The one gap is sibling sing_probe — the description never says when that tool is the better choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.