Skip to main content
Glama

FreqBlog Music Metadata

by com.freqblog
OverviewDiscussionsAdmin

Tag Track

tag_track
Read-only

Get a compact, HONESTLY-LABELLED tag list for a track — energy / danceability / valence / acousticness, plus a mood tag and a broad genre tag (instrumentalness is currently null, so it is not tagged). It is a tag-shaped projection of the same open-data analysis get_audio_features returns (no audio upload, no extra compute), so it costs the same 1 quota unit, charged only on a served result.

The differentiator vs opaque taggers (e.g. Cyanite) is that EVERY tag carries its own
`confidence` and `provenance`:
  - confidence: measured (our Essentia analysis) | derived (MIREX mood from valence+energy) |
    model-estimated (AcousticBrainz mood SVM probability — research-grade, raw prob in `value`) |
    catalog-genre (broad catalogue tag, not fine-grained).
  - provenance: essentia | valence+energy | acousticbrainz | catalog.
`value` is the [0,1] score for numeric tags and null for label-only tags (mood category, genre).

Provide AT LEAST ONE identifier: `track` (optionally with `artist`), `isrc`, `mbid`,
`spotify_id`, or `track_id` (catalog itunes_track_id). If you know several, send them all —
they resolve by precedence (`track` > `isrc` > `track_id` > `mbid` > `spotify_id`) and the
rest are ignored, so you never have to pick. The broad, reliable coverage is the
MEASURED tags from our Essentia analysis over the analysed catalogue (plus on-demand by name);
MBID/ISRC additionally reach 7.5M+ AcousticBrainz recordings WHEN you supply that identifier.

Returns { track, count, tags:[{tag, category, value, confidence, provenance}], disclaimer }.
For the full numeric feature set use get_audio_features; for nearest tracks use a discovery tool.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
isrcNoISRC, e.g. 'USUM71900001'.
mbidNoMusicBrainz recording ID (UUID). Tags come from AcousticBrainz for that exact recording.
trackNoTrack title. Use with `artist` when known. Supply AT LEAST ONE of track/isrc/mbid/spotify_id/track_id. Sending several is fine — they resolve by precedence (track > isrc > track_id > mbid > spotify_id).
artistNoArtist name. Only used with `track`; improves accuracy.
track_idNoCatalog itunes_track_id from a search_catalog or get_audio_features result.
spotify_idNoSpotify track ID, 'spotify:track:...' URI, or open.spotify.com URL. Resolved per request by reading the track's title from Spotify's public embed page and matching it against our catalogue (no Spotify IDs are stored) — a title several artists share is ambiguous and misses rather than guessing; prefer track (+artist) or isrc.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / spotify_id / description
      Previous value: -"Spotify track ID, 'spotify:track:...' URI, or open.spotify.com URL. Resolved from our Spotify-ID map or, on a miss, by matching the track's title — a title several artists share is ambiguous and misses rather than guessing; prefer track (+artist) or isrc."New value: +"Spotify track ID, 'spotify:track:...' URI, or open.spotify.com URL. Resolved per request by reading the track's title from Spotify's public embed page and matching it against our catalogue (no Spotify IDs are stored) — a title several artists share is ambiguous and misses rather than guessing; prefer track (+artist) or isrc."
  2. Changed1 schema field changed
    • changedInput schema / properties / spotify_id / description
      Previous value: -"Spotify track ID, 'spotify:track:...' URI, or open.spotify.com URL. Resolves ONLY tracks already mapped to a Spotify ID (<1% of the catalog) — prefer track (+artist) or isrc."New value: +"Spotify track ID, 'spotify:track:...' URI, or open.spotify.com URL. Resolved from our Spotify-ID map or, on a miss, by matching the track's title — a title several artists share is ambiguous and misses rather than guessing; prefer track (+artist) or isrc."
  3. Changed1 schema field changed
    • changedInput schema / properties / track / description
      Previous value: -"Track title. Use with `artist` when known. Required field is ONE of track/isrc/mbid/spotify_id/track_id."New value: +"Track title. Use with `artist` when known. Supply AT LEAST ONE of track/isrc/mbid/spotify_id/track_id. Sending several is fine — they resolve by precedence (track > isrc > track_id > mbid > spotify_id)."
  4. Changed1 schema field changed
    • changedInput schema / properties / spotify_id / description
      Previous value: -"Spotify track ID, 'spotify:track:...' URI, or open.spotify.com URL. Resolves ONLY tracks already mapped to a Spotify ID (~2.4% of the catalog) — prefer track (+artist) or isrc."New value: +"Spotify track ID, 'spotify:track:...' URI, or open.spotify.com URL. Resolves ONLY tracks already mapped to a Spotify ID (<1% of the catalog) — prefer track (+artist) or isrc."
  5. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover readOnlyHint, but the description adds substantial behavioral detail beyond them: quota cost (1 unit, charged only on a served result), no audio upload/compute, the four confidence/provenance classes, the instrumentality null gap, and the different coverage of Essentia vs AcousticBrainz depending on identifier supplied. This is unusually rich disclosure for a read tool.

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?

Purpose, cost model and differentiator are front-loaded, and the confidence/provenance bullets earn their space. It is long and includes a little redundancy (the compute/upload caveat and the identifier rules appear twice across description and schema), but there is no padding sentence that could be dropped without losing information.

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?

With an output schema present, return values need not be described, yet the description still summarizes the shape and explains the semantics of value/confidence/provenance that the schema alone would not convey. For a 6-param read tool with open-world resolution behavior, nothing essential is missing.

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 description coverage is 100%, so the baseline is 3, but the description adds real value by tying identifier choice to outcome: precedence order (track > isrc > track_id > mbid > spotify_id), the 'send them all, you never have to pick' affordance, and the fact that MBID/ISRC unlock 7.5M+ AcousticBrainz recordings. It largely reinforces schema text but the coverage consequence is new meaning.

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 gives a specific verb and resource ('Get a compact, HONESTLY-LABELLED tag list for a track') and immediately enumerates the returned tag types. It explicitly separates itself from siblings get_audio_features ('full numeric feature set') and the discovery tools, so an agent can pick it without opening a schema.

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 routes clearly: use get_audio_features for the full feature set, a discovery tool for nearest tracks, and this tool for labelled tags. It also explains identifier precedence so the caller doesn't have to choose. It stops short of explicit when-not-to-use conditions or prerequisites (e.g., when tags will be empty), but the alternative-naming is strong.

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

All FreqBlog Music Metadata toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources