commendation

Overview Schema Source Related Servers Discussions Admin

recommend_from_song

Find new songs similar to a seed song by title, artist, or video ID, ranked by matching signals. Filters by language and tempo, and excludes songs already liked or in playlists.

Instructions

Recommend new songs similar to a seed song.

Seed the search either with a known video_id, or with song (a free-text title, optionally narrowed with artist) to have the seed resolved via search internally -- e.g. "10 songs that relate to Kryptonite by 3 Doors Down" needs no separate lookup first. Exactly one of video_id or song must be given.

Combines YouTube Music's radio, its separate "related" signal, and the seed artist's own catalog plus related artists' catalogs, then ranks by how many independent signals agreed on each candidate. Never returns the seed song itself, and never returns a song already in Liked Music or in ANY of the user's playlists.

By default candidates can come from OTHER artists too (radio/related signals surface stylistically similar tracks, not just the seed artist's own catalog) -- pass same_artist_only=True to keep only songs credited to the seed's own artist(s), e.g. for "recommend songs BY artist X similar to song Y" requests.

language / exclude_languages filter the RESULTS independently of the seed, which is the point: seeding from a Punjabi song with language=["english"] returns English songs similar to it. Strict by default -- candidates with no language label are dropped, since a Punjabi-seeded pool is mostly Punjabi and keeping unlabelled ones would hand back exactly what was excluded. Pass allow_unlabelled_language=True to relax that; the response always reports what was dropped.

When a language filter leaves too few results -- seeding from a Punjabi song and asking for English usually does -- the surviving songs are used as fresh seeds to reach more of that language in the same neighbourhood, since filtering alone can only return what happened to be in the seed's own pool. Set expand_across_language=False to skip that and get the short list.

match_seed_tempo=True biases results toward the seed's own BPM (half- and double-time count as close). bpm sets a tempo target directly, and bpm_min/bpm_max bound it. Songs with no known BPM are kept and simply not scored on tempo.

Returns {"songs": [...], "notes": [...], "filters": {...}} -- notes carry anything the user should hear about, such as results dropped for having no language label.

The library exclusion set is cached for speed; newly liked songs are always honoured, but call refresh_library() after adding songs to a playlist by other means.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`bpm`	No
`song`	No
`limit`	No
`artist`	No
`bpm_max`	No
`bpm_min`	No
`language`	No
`video_id`	No
`max_per_artist`	No
`match_seed_tempo`	No
`same_artist_only`	No
`exclude_languages`	No
`expand_across_language`	No
`allow_unlabelled_language`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Sep 13, 2026

TDQS

A4.3/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the multi-signal ranking strategy, that the seed song is never returned, exclusion of Liked Music and all playlists, the default cross-artist behaviour, language-filter strictness with allow_unlabelled_language escape hatch, and the response shape with notes. It even flags a cache-staleness behaviour and the refresh_library() remedy — exactly the kind of non-obvious trait annotations would normally supply.

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 and the required-argument rule are front-loaded, and essentially every sentence adds a distinct behavioural fact, so length is largely justified. A few conversational asides ('which is the point:') and repeated restatements of the language-filter rationale could be trimmed 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?

An output schema exists so return values need not be re-explained, and the description nonetheless names the response keys and the role of `notes`. Combined with the mutual-exclusion rule, filter semantics, and the cache/refresh_library dependency, an agent has everything needed to call this 14-parameter tool correctly.

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 0% across 14 parameters, so the description is the only source of meaning, and it explains the semantics of most of them: video_id vs song mutual exclusion, artist narrowing, language/exclude_languages independence from the seed, allow_unlabelled_language, expand_across_language, same_artist_only, and match_seed_tempo/bpm/bpm_min/bpm_max including the half/double-time and missing-BPM cases. It leaves `limit` and `max_per_artist` (the default of 2) undocumented.

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

Purpose4/5

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

The first sentence gives a specific verb and resource ('Recommend new songs similar to a seed song'), which cleanly separates it from the playlist- and mood-seeded siblings by seeding resource. It never names those siblings explicitly, so an agent must infer the routing from the resource noun rather than being told.

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?

Strong in-scope guidance: exactly one of video_id or song must be given, with a worked example ('10 songs that relate to Kryptonite by 3 Doors Down'); it also explains when same_artist_only, language filters, and expand_across_language apply. It does not, however, compare itself against the sibling tools (recommend_from_playlist, recommend_for_mood), so the agent gets no explicit alternative routing.

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

Deploy Server