Search, analyze, and discover commercially released music using sonic intelligence.
Scored across 4 tools
Each tool targets a distinct resource and action: describing a track, finding playlists by intent, finding similar artists, and finding similar tracks. The track-vs-artist similarity split is clear, and the descriptions reinforce the boundaries without overlap.
All tool names use snake_case and follow a verb_noun pattern, with three tools sharing the consistent find_ prefix and one using describe_. The convention is predictable and readable throughout.
Four tools is compact and well-scoped for a focused music discovery and analysis server. Each tool covers a distinct core intent, with no redundant or filler operations.
The set covers track description, playlist discovery, and artist/track similarity, but it lacks operations for inspecting playlist contents, retrieving detailed artist or track metadata, or performing general entity lookup. These gaps may force agents to stop short on follow-up requests such as showing tracks inside a found playlist.
Analyze and describe how a specific released track sounds. Use when a user asks about a song's sonic or musical characteristics, genre, BPM, key, mode, loudness, intensity, frequency characteristics, or possible musical influences.
| Name | Required | Description | Default |
|---|---|---|---|
| track | Yes | The track title. | |
| artist | Yes | The artist name. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false) and the open-world nature of the lookup. The description adds the valuable disclosure that analysis targets released tracks and enumerates the categories of attributes returned (genre, BPM, key, mode, loudness, intensity, frequency characteristics, influences). It stops short of stating latency, caching, or what happens on unknown tracks.
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?
Two sentences, zero filler, with the core action front-loaded before the usage trigger. Every clause 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?
With no output schema and a simple two-parameter read tool, the description compensates well by naming the facets it returns. It is complete enough to call and interpret correctly, though it omits failure behavior for ambiguous or unreleased tracks.
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 100% and both parameters carry their own descriptions ('The track title.', 'The artist name.'), so the description adds no syntax or format detail beyond the schema. Baseline 3 is appropriate.
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?
States a specific verb+resource ('Analyze and describe ... a specific released track') with a clear scope constraint ('released'). This is easily distinguished from the sibling find_* tools, which locate entities rather than describe audio characteristics.
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?
Explicitly gives a trigger condition ('Use when a user asks about a song's sonic or musical characteristics') and enumerates the qualifying facets (genre, BPM, key, loudness, influences). It does not name alternatives or when-not to use it, but the find_* siblings are functionally distinct enough that routing is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find MusicAtlas playlists for a user's musical intent. Use this whenever a user asks for playlists based on a mood, theme, genre, activity, vibe, geography, artist, or track. For natural-language requests such as 'playlists about love', 'workout playlists', or 'sad indie', pass the meaningful musical concept as tags. This tool can also find playlists associated with a specific artist or track.
| Name | Required | Description | Default |
|---|---|---|---|
| geo | No | Optional geographic or regional context for playlist discovery. | |
| tags | No | Natural-language playlist theme, mood, genre, activity, or vibe. Examples: 'love', 'workout', 'sad indie'. | |
| track_name | No | Track title when looking up playlists associated with a specific track. | |
| artist_name | No | Artist name when looking up playlists associated with a specific artist. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint and destructiveHint, so the safety profile is covered. The description adds genuinely non-structured behavior: that arbitrary natural-language concepts should be passed as tags and that the tool also resolves playlists via artist or track. Return volume, ranking, and result limits are still undisclosed.
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?
Three tight sentences, front-loaded with the purpose, then usage triggers, then the artist/track case. No filler and nothing repeated from the schema.
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?
A read-only discovery tool with four optional params and no output schema; the description covers intent, triggers, and how to shape input. It omits what happens when several params are combined and whether results are ranked or limited, which an agent would need to interpret output confidently.
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 100%, so the baseline is 3. The description goes beyond the schema by prescribing the interpretation rule — map the user's meaningful musical concept into `tags` rather than paraphrasing it — which is real semantic guidance the schema alone does not convey.
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?
States a specific verb+resource ('Find MusicAtlas playlists') and scopes it to a user's musical intent. The resource is clearly distinct from the track/artist-oriented siblings (describe_track, find_similar_artists, find_similar_tracks), so an agent can route without opening the schema.
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?
Strong trigger enumeration: 'use this whenever a user asks for playlists based on a mood, theme, genre, activity, vibe, geography, artist, or track', with concrete NL examples ('playlists about love', 'workout playlists', 'sad indie'). No explicit when-not or named alternative, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find artists that are similar, sonically related, or musically adjacent to a specific artist. Use when a user asks for artists like or similar to a named artist. Results include ranked artist matches, MusicAtlas artist URLs, and supporting track examples.
| Name | Required | Description | Default |
|---|---|---|---|
| artist | Yes | The reference artist name. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, openWorld, and non-destructive, so safety is covered. The description adds value by disclosing the return content (ranked matches, MusicAtlas URLs, supporting track examples), which is not in any structured field.
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?
Three tight sentences, front-loaded with purpose then usage. The opening triple of near-synonyms ('similar, sonically related, or musically adjacent') is slightly redundant but not costly.
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?
For a single-parameter, read-only lookup with no output schema, the description covers purpose, trigger, and return shape adequately. It omits any mention of result limits or ranking behavior, but nothing critical for invocation is missing.
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?
Only one parameter exists and schema coverage is 100%, so the schema fully documents it; the description adds only the notion of a 'reference artist,' which is already conveyed by the schema 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?
States a specific verb (find) and resource (artists) with a clear scope modifier ('similar, sonically related, or musically adjacent to a specific artist'). It implicitly separates itself from find_similar_tracks by resource, but never explicitly names or contrasts the sibling.
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?
Gives an explicit trigger: 'Use when a user asks for artists like or similar to a named artist.' However, it offers no when-not guidance and does not mention find_similar_tracks as the adjacent alternative for track-level queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find songs or tracks that sound similar to, resemble, or are sonically related to a specific released recording. Use when a user asks for songs like a particular track or wants similarity-based track recommendations. MusicAtlas performs canonical track resolution and audio-based similarity search.
| Name | Required | Description | Default |
|---|---|---|---|
| track | Yes | The title of the reference track. | |
| artist | Yes | The artist name for the reference track. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/openWorld/destructive, so the safety profile is covered. The description adds real behavioral context beyond them: MusicAtlas performs canonical track resolution and audio-based similarity search, implying fuzzy title/artist matching. It doesn't say how many results come back or how they're ranked.
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?
Three compact sentences with the core purpose leading. The third sentence about canonical resolution is useful but slightly backend-flavored; otherwise no waste.
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?
No output schema exists, so the description should ideally hint at the return shape (a ranked track list, count, scoring). It describes the input side and the matching mechanism but leaves results opaque, which is a gap for a search-type tool.
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 100% and both parameters are self-documented ('title of the reference track', 'artist name'). The description adds no format, disambiguation, or matching guidance beyond what the schema already provides, so the baseline 3 applies.
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?
States a specific verb and resource: 'Find songs or tracks that sound similar to ... a specific released recording.' The track-versus-artist distinction implicitly separates it from find_similar_artists, but no sibling is named explicitly.
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?
Gives a clear triggering condition ('Use when a user asks for songs like a particular track or wants similarity-based track recommendations'). It stops short of stating when NOT to use it or naming find_similar_artists as the alternative for artist-level queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
describe_trackfind_playlistsfind_similar_artistsfind_similar_tracksPrivacy-first audio intelligence: BPM, key, waveform. Audio never stored. Pay per second.
Audio features + harmonic set-building for tracks by name/ISRC. Spotify audio-features replacement.
Analyze tracks and manage customer music-promotion workflows through your DropTrack account.
Spotify: Spotify Data API for Millions of songs & podcasts, artists, albums, playlists and more.
Add one secure layer between your agents and this server.
