Skip to main content
Glama
crates-music-mcp

crates-music-mcp

by guohangbk

search_songs

Search QQ Music, NetEase, or Kugou for songs by title or title plus artist. Returns platform song IDs, artist names, and albums so you can confirm a track exists before adding it to a playlist.

Instructions

在某个平台搜歌,返回可直接喂给建单/加歌的候选。

service: qq_music | netease | kugou keyword: 歌名、或「歌名 歌手」 limit: 返回条数(默认 10,最多 50) Returns {"ok","service","count","songs":[{"name","artist","id","album"}]}。 id 是该平台的歌曲标识(QQ songid / 网易云 song id / 酷狗 hash)。 想确认"某首歌在平台上到底有没有、是哪一首"时用它。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "service": "<service>",
      "keyword": "<keyword>"
    },
    "name": "search_songs"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
keywordYes
serviceYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a good job: it discloses the exact response envelope, the per-platform meaning of the returned id (QQ songid / netease song id / kugou hash), and the limit ceiling. It does not mention login/cookie prerequisites or rate limits, which matters given the credential_* and login_* siblings in the same catalog.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then a compact parameter legend, then return shape and the id-semantics note that actually matters for downstream calls. Slightly repetitive in restating the return shape, but there is no filler sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter read tool with an output schema, the description is nearly sufficient, and the id-semantics note is genuinely useful. The gap is authentication: with no annotations and login/credential tools present in the catalog, an agent cannot tell from this definition whether a session is required before searching, which is the most likely cause of a failed call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does for all three parameters: service lists the valid platform values, keyword specifies the accepted format (song name, or "song name artist"), and limit gives both the default of 10 and the hard maximum of 50. That is meaningfully beyond the bare schema types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb and resource (搜歌 on a given platform) plus the downstream value (returns candidates directly usable for playlist creation/adding songs). The closing sentence narrows the intent further to existence/identity verification, so an agent can tell exactly what this tool is for versus playlist-mutating siblings like add_songs_to_playlist.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly names the scenario that selects this tool: when you need to confirm whether a song exists on a platform and which version it is. It also implies the feed-forward relationship to playlist-building tools. It stops short of naming a sibling to use instead or stating exclusions, so it is clear context rather than full routing guidance.

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