Find tracks that fit a SET of 2-8 tracks together (their combined sound / centroid), not similarity to a single seed. Pass 2-8 Bandcamp/YouTube/SoundCloud links.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral context: it explains the underlying logic (combined sound/centroid instead of single-seed similarity) and specifies input requirements (2-8 links from specific platforms). This enriches the agent's understanding beyond the safety profile provided by annotations.
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 extremely concise (two sentences, ~40 words) with zero filler. The key functional distinction (set-based vs single-seed) is front-loaded in the first sentence, and the concrete input guide follows immediately. Every sentence earns its place.
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 tool's complexity (set similarity), 1 required parameter with 0% schema coverage, and presence of an output schema, the description covers the core semantics and constraints thoroughly. It does not explain return value format, but that is acceptable because an output schema exists. The only minor gap is no mention of error handling (e.g., invalid links).
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 coverage is 0% (no description in schema), so the description must fully compensate. It does so excellently by explaining that the 'urls' parameter must contain 2-8 Bandcamp/YouTube/SoundCloud links, adding constraints like min/max count and supported platforms. This adds critical meaning absent from the bare schema, making the parameter actionable.
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 explicitly states the tool finds tracks fitting a combined set (centroid) of 2-8 tracks, not similarity to a single seed. It names specific supported platforms (Bandcamp, YouTube, SoundCloud) and uses specific verb 'Find' with clear resource ('tracks') and scope ('SET of 2-8 tracks'). This strongly differentiates from siblings like 'find_similar' (single seed) and 'deep_match'.
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 description provides clear context for when to use this tool: 'Find tracks that fit a SET of 2-8 tracks together... not similarity to a single seed' and specifies the exact format needed ('Pass 2-8 Bandcamp/YouTube/SoundCloud links'). It implies not to use with a single track or with unsupported platforms, but does not explicitly name sibling alternatives nor state when-not-to-use in negative terms.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes: deep_match for technical DJ matching, find_similar for general sonic similarity, generate_playlist for creating full sets, inspire_me for personalized discovery, playlist_match for multi-track centroid matching, and surprise_me for broad discovery. However, inspire_me and surprise_me both relate to discovery with overlap in scope, causing minor ambiguity.
Tool names use a mix of verbs and descriptive phrases (deep_match, find_similar, generate_playlist, inspire_me, playlist_match, surprise_me). The pattern is not fully consistent; some use verb_noun (generate_playlist) while others use verb_adjective (find_similar) or are more abstract (inspire_me). Not chaotic but lacks a uniform structure.
6 tools is well-scoped for a music discovery server. Each tool covers a specific function without redundancy, covering technical matching, similarity search, playlist generation, personalized discovery, group matching, and broad exploration. The number feels balanced and appropriate.
The tools cover core music discovery workflows: single-track matching, multi-track centroid matching, playlist generation with energy flow, and personalized/random discovery. Minor gaps include lack of explicit CRUD for user playlists beyond generation and no tools for browsing or managing user history directly.
