Skip to main content
Glama

FreqBlog Music Metadata

Find Similar-Sounding Tracks

find_similar_tracks
Read-only

Tracks that SOUND like one seed track or a set of up to 10, optionally restricted by tempo, key, genre, year, chart or audio-feature ranges — e.g. "like these three, but 120-128 BPM in 8A or its neighbours": seed_tracks=[...], min={"tempo": 120}, max={"tempo": 128}, key="8A", harmonic=true.

Ranked mainly on a PANNs audio embedding (how the recording sounds) blended with an
audio-feature similarity. Results are one per recording, with `score`, `genre_relation`
to the seed and, with several seeds, `matched_seed`. With filters, results are the
closest-sounding tracks that pass every filter, and `filters` reports what was applied
and how many catalog tracks each one removed (`dropped_by`) — loosen the largest if the
list is short. Use get_recommendations instead when you want preferred target values
(target energy etc.) rather than hard filters. Costs 1 quota unit.
PANNs (Kong et al., 2020) is used under CC BY 4.0.

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": "find_similar_tracks"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoFilter — comma list of keys: Camelot ('8A'), Open Key ('1m') or names ('A minor').
maxNoFilter — HARD upper bounds, e.g. {'tempo': 128}. Same attributes as `min`.
minNoFilter — HARD lower bounds on the results, e.g. {'tempo': 120, 'energy': 0.6}. Attributes: acousticness, danceability, duration_ms, energy, loudness, tempo, valence.
modeNoFilter — 'major' or 'minor' only.
blendNoWith several seeds: 'all' (default) = sounds like the set as a whole, best when the seeds share a style; 'any' = every seed gets its own neighbours, interleaved — use it when the seeds are from different genres, where 'all' would average them into tracks that sound like none of them.all
genreNoFilter — comma list of catalog genre names, e.g. 'house'. Unknown names in a list are skipped and listed in filters.ignored with close matches; only a list where every name is unknown is rejected.
limitNoResults to return (default 10).
chartedNoFilter — true = only tracks with a known chart placement.
explicitNoFilter — true = explicit only, false = non-explicit only.
harmonicNoWiden each key to its harmonically compatible keys.
max_yearNoFilter — latest release year.
min_yearNoFilter — earliest release year.
track_idNoOne seed: a catalog itunes_track_id (from search_catalog or get_audio_features). Omit when using seed_tracks / seed_isrcs.
seed_isrcsNoSeveral seeds by ISRC (up to 10 together with seed_tracks).
cross_genreNoGenre lane: 'auto' (default, keep results mixable with the seed's genre), 'allow' (genre-blind), 'strict' (seed's genre family only).auto
seed_tracksNoSeveral seeds: catalog itunes_track_ids (up to 10 together with seed_isrcs).
tempo_matchNoWith a tempo bound: 'exact' (default) or 'half_double' (also match double/half the range).exact
min_chart_peakNoFilter — best chart position required, as chart_peak (100 = a number one).
include_subgenresNoAlso match every subgenre of a top-level genre.
exclude_same_artistNoDrop other tracks by the seed artist(s).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / genre / description
      Previous value: -"Filter — comma list of catalog genre names, e.g. 'house'. An unknown name is rejected with close matches."New value: +"Filter — comma list of catalog genre names, e.g. 'house'. Unknown names in a list are skipped and listed in filters.ignored with close matches; only a list where every name is unknown is rejected."
  2. Changed1 schema field changed
    • changedInput schema / properties / blend / description
      Previous value: -"With several seeds: 'all' (default) = sounds like the whole set; 'any' = like any one seed, interleaved so each is represented."New value: +"With several seeds: 'all' (default) = sounds like the set as a whole, best when the seeds share a style; 'any' = every seed gets its own neighbours, interleaved — use it when the seeds are from different genres, where 'all' would average them into tracks that sound like none of them."
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, and the description adds substantially beyond that: the ranking mechanism, the one-result-per-recording dedupe, the returned fields (score, genre_relation, matched_seed), the filters/dropped_by diagnostic block, and the cost ('1 quota unit'). That is exactly the operational context annotations cannot convey.

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 mechanism, then the worked example, then the sibling alternative — a sensible order. It is dense but long, and the trailing CC BY 4.0 attribution line is legal boilerplate that does not help an agent decide or call correctly.

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 a 20-parameter, filter-heavy search tool with an output schema, the description covers what an agent needs: seed options, filter interaction, ranking basis, result shape, cost, and the fallback tool. Nothing required to invoke it correctly 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; the description earns above that by showing a worked combination (seed_tracks + min/max tempo + key + harmonic) that demonstrates how filters compose rather than what each one means. It does not add new per-parameter detail beyond the schema, so it stops short of 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?

Opens with a specific verb+resource ('Tracks that SOUND like one seed track or a set of up to 10'), states the ranking signal (PANNs audio embedding blended with audio-feature similarity), and explicitly contrasts itself with get_recommendations. An agent can distinguish this from search_by_description or suggest_next_track without opening any schema.

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?

Gives an explicit routing rule: 'Use get_recommendations instead when you want preferred target values (target energy etc.) rather than hard filters.' It also covers the multi-seed decision via blend ('all' for same-style seeds, 'any' for cross-genre) and tells the agent how to recover from a short result list by loosening the filter with the largest dropped_by.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources