Skip to main content
Glama
@jam-jam/convert-mcp

@jam-jam/convert-mcp

by titouannwtt

Analyse a track for AI music signals

jj_ai_music_analyze

Start AI music detection on a local audio file or supported link, then track the asynchronous job to get a signal-based report. Supports path, base64, Spotify, ISRC, or direct audio URL.

Instructions

Starts an AI music detection (POST /ai-music/jobs) on a local audio file (path, or base64 content: 100 MB and 600 seconds at most), OR on exactly one link: "url" (Spotify track link), "spotifyTrackId", "isrc" or "audioUrl" (direct audio link; YouTube is not supported; a Spotify or ISRC source may only provide an excerpt, see result.primary.audioSource). Links only work when jj_ai_music_availability reports links=true. Asynchronous: returns at once with a job (pass maxWaitMs to wait), then follow it with jj_ai_music_get_job. One unfinished analysis per account at a time (409), results kept 90 days, no audio kept. Needs the audio:write scope. Consumes one unit of the ai-music counter (free 5/day and 50/month, Premium 30/day and 300/month, UTC; failures refunded); a 429 states when it resets, a 413 means the file is too large or too long. The report is an aggregated index of signals, not a probability and not proof of origin: present it as such.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "jj_ai_music_analyze"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoSpotify track link. Exclusive with every other source.
isrcNoISRC code of the recording. Exclusive with every other source.
pathNoAbsolute or relative local path to the audio file. Exclusive with contentBase64 and the link fields.
audioUrlNoDirect link to an audio file. Exclusive with every other source.
filenameNoFile name (with extension). Required with contentBase64; defaults to the basename of "path".
maxWaitMsNoWait up to this long (milliseconds, cap 600000) for the analysis to finish. Default 0: return at once.
contentBase64NoBase64-encoded audio. Exclusive with path and the link fields. Requires "filename".
spotifyTrackIdNoSpotify track id. Exclusive with every other source.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided the description carries the full burden, and it does: async job semantics, one unfinished analysis per account (409), 90-day result retention, no audio retained, audio:write scope, a metered counter with free/Premium tiers and refunds on failure, plus 429 and 413 meanings. It also warns that the output is an aggregated index of signals, not a probability or proof of origin — a material interpretive constraint an agent could not otherwise infer.

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?

Dense and front-loaded — sources, then constraints, then async behavior, then quota/errors, then the interpretation caveat. Every sentence carries information, but it is delivered as one long run-on paragraph where semicolons and parentheticals stack up; splitting the operational constraints from the quota/error notes would improve scanability.

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

Completeness5/5

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

For an 8-parameter, no-output-schema, metered asynchronous tool, nothing essential is missing: source selection, size/duration limits, wait behavior, follow-up tool, concurrency limit, retention, auth scope, quota accounting, and error codes are all covered. The description even tells the agent how to frame the returned report, which compensates for the absent output schema.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns above that by adding meaning the schema lacks: the 100 MB / 600-second caps, the mutual exclusivity rule across all four link fields and path/contentBase64, and the caveat that Spotify or ISRC sources may yield only an excerpt (visible via result.primary.audioSource). It stops short of explaining every parameter (e.g. maxWaitMs interaction with job follow-up is only implied), so not a 5.

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 description opens with a specific verb plus resource ("Starts an AI music detection") and even names the backing endpoint (POST /ai-music/jobs). It immediately enumerates the accepted source types (local path, base64 content, or exactly one link: url/spotifyTrackId/isrc/audioUrl), which distinguishes it from jj_ai_music_availability and jj_ai_music_get_job without either schema being opened.

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

Usage Guidelines5/5

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

It explicitly routes the agent: use links only when jj_ai_music_availability reports links=true, and follow up with jj_ai_music_get_job after the async return. It also states exclusions directly ("YouTube is not supported", "exactly one link") and clarifies that maxWaitMs is the option for waiting inline.

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