get_song_radioCreate a radio playlist from YouTube Music by entering a song query, with ordered recommendations built around the first matching track.
Get YouTube Music's ordered radio recommendations around the first song match.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| seed | Yes | ||
| tracks | Yes | ||
| returned | Yes | ||
| requested | Yes |
Changes observed during successful MCP inspections.
v0.3.0Output schema / $defs / TrackResult / properties / albumAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Album"
+}Output schema / $defs / TrackResult / properties / duration_secondsAdded value: +{
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Duration Seconds"
+}Output schema / $defs / TrackResult / requiredPrevious value: -[
- "videoId",
- "title",
- "artists",
- "duration",
- "url"
-]New value: +[
+ "videoId",
+ "title",
+ "artists",
+ "album",
+ "duration",
+ "duration_seconds",
+ "url"
+]v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the description only needs to add behavior beyond safety and openness. It does add useful detail: the radio is 'ordered' and centered on the 'first song match,' which clarifies how the query is resolved. It does not disclose edge cases like no-match behavior, but with the annotations and output schema present, this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one sentence with no filler, and it front-loads the core purpose before the qualifying detail. Every word contributes either to what the tool does or to how it behaves ('ordered', 'first song match').
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema, the readOnly/openWorld annotations, and a simple two-parameter interface, the description is nearly sufficient for selection. It is missing explicit semantics for 'limit' and does not cover failure/no-match behavior, so it is adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must carry parameter meaning. It explains the role of 'query' only indirectly through 'first song match,' but it never explains 'limit' or that the limit controls how many radio recommendations to return. This leaves a meaningful part of the input interface undocumented in both schema and description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies a concrete verb ('Get'), a resource ('YouTube Music radio recommendations'), and a distinguishing qualifier ('around the first song match'), which separates it from the multi-seed sibling. It is slightly less explicit than it could be because it does not name any sibling, but the single-seed emphasis is enough to orient an agent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'around the first song match' implies this is for single-song-seeded radio as opposed to multi-seed radio, but it never states that tradeoff explicitly. It offers no guidance on when to prefer search_songs or when to use a private playlist tool. The usage context is implied rather than spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.