Skip to main content
Glama

search_music

Use this when the user needs existing, licensable music or sound effects for a project — background music, production music, music for an ad, trailer, YouTube video, podcast, game or film — described in words (mood, scene, genre, instruments, energy). Do not use it to generate new music, write lyrics, identify a song, or play commercial releases by other artists. Find AINSOF music from a written brief — mood, scene, genre, energy, instruments. Example: 'lo-fi hip hop underscore, warm, no vocals'. Send the user's original language and musical intent, including durations and exclusions. Each call is self-contained. For a refinement, combine the current musical requirements and the latest change into brief; do not send only the clarification question. Send only musical requirements, never chat transcripts, assistant replies or unrelated personal information. Pass the customer's musical request in their original language, preserving their words, exclusions and durations. Do not add instruments, genres, mood, energy or vocal restrictions that they did not ask for. For a refinement, combine only the customer's established requirements and latest change, not suggestions from an assistant. One search returns evaluated matches or alternatives; present that result before proposing another direction. An unavailable search is a technical failure, not an empty catalog: explain it and do not automatically repeat or broaden the request. A user-requested retry remains possible. Use the returned understanding, followups and selected preview version when presenting the answer. A NAME also works, and is answered exactly: pass a track title ('Shine On Today'), an album ('Shining Ahead'), a catalog number ('AIN-CAT 031') or a COMPOSER ('Alon Peretz') as the brief and you get that cue, that album in full, or everything that writer wrote. A composer named inside an ordinary brief puts their cues first without narrowing it. NEVER tell a user we do not have a track until you have passed its name here.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "brief": "<brief>"
    },
    "name": "search_music"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefYesWhat the music should be — or the exact name of a track, album or catalog number.
scopeNoOptional library restriction; omit to let the request select the library.
top_kNoNumber of candidates requested. Discovery searches return at least fifteen, closest first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / top_k / default
      Previous value: -8New value: +15
    • changedInput schema / properties / top_k / description
      Previous value: -"Number of candidates requested. Discovery searches normalize values below eight to eight."New value: +"Number of candidates requested. Discovery searches return at least fifteen, closest first."
  2. Changed2 schema fields changed
    • changedInput schema / properties / top_k / default
      Previous value: -10New value: +8
    • addedInput schema / properties / top_k / description
      Added value: +"Number of candidates requested. Discovery searches normalize values below eight to eight."
  3. Changed1 schema field changed
    • changedInput schema / properties / brief / description
      Previous value: -"What the music should be — or the exact name of a track, album or catalogue number."New value: +"What the music should be — or the exact name of a track, album or catalog number."
  4. Changed3 schema fields changed
    • removedInput schema / properties / clarification
      Removed value: -{
      -  "maxLength": 500,
      -  "type": "string"
      -}
    • removedInput schema / properties / continue_previous
      Removed value: -{
      -  "type": "boolean"
      -}
    • removedInput schema / properties / history
      Removed value: -{
      -  "description": "Only the current search conversation, in order. Include the original user brief; mark its first user turn contextStart=true. Exclude older topics.",
      -  "items": {
      -    "properties": {
      -      "answerTo": {
      -        "maxLength": 500,
      -        "type": "string"
      -      },
      -      "contextStart": {
      -        "description": "True on the first user turn of the active search topic.",
      -        "type": "boolean"
      -      },
      -      "role": {
      -        "enum": [
      -          "user",
      -          "assistant"
      -        ],
      -        "type": "string"
      -      },
      -      "text": {
      -        "maxLength": 600,
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "role",
      -      "text"
      -    ],
      -    "type": "object"
      -  },
      -  "maxItems": 8,
      -  "type": "array"
      -}
  5. Changed6 schema fields changed
    • addedInput schema / properties / clarification
      Added value: +{
      +  "maxLength": 500,
      +  "type": "string"
      +}
    • addedInput schema / properties / continue_previous
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / history
      Added value: +{
      +  "description": "Only the current search conversation, in order. Include the original user brief; mark its first user turn contextStart=true. Exclude older topics.",
      +  "items": {
      +    "properties": {
      +      "answerTo": {
      +        "maxLength": 500,
      +        "type": "string"
      +      },
      +      "contextStart": {
      +        "description": "True on the first user turn of the active search topic.",
      +        "type": "boolean"
      +      },
      +      "role": {
      +        "enum": [
      +          "user",
      +          "assistant"
      +        ],
      +        "type": "string"
      +      },
      +      "text": {
      +        "maxLength": 600,
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "role",
      +      "text"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 8,
      +  "type": "array"
      +}
    • addedInput schema / properties / scope
      Added value: +{
      +  "description": "Optional library restriction; omit to let the request select the library.",
      +  "enum": [
      +    "music",
      +    "sfx"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / top_k / maximum
      Added value: +40
    • addedInput schema / properties / top_k / minimum
      Added value: +1
  6. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations (openWorldHint=true, idempotentHint=false), the description discloses that each call is self-contained, that a failed search is a technical failure rather than an empty catalog, that results must be presented before proposing another direction, and that returned understanding/followups/preview version should drive the answer. It does not mention any cost, quota or credit consumption, which is the main remaining behavioral unknown for an open-world, non-idempotent search.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical content is front-loaded, but the body is long and repeats itself: the brief-construction rule appears in at least three variants ('send the user's original language and musical intent', 'pass the customer's musical request in their original language', 'for a refinement, combine the current musical requirements and the latest change'). The 'Find AINSOF music from a written brief — mood, scene, genre, energy, instruments' sentence restates the opening paragraph almost verbatim.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter open-world search with no output schema, the description covers purpose, input construction, failure semantics and how to present results, including naming the returned fields (understanding, followups, selected preview version). What is missing is operational context such as whether calls consume quota or how many attempts are reasonable, which matters for a non-idempotent tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the schema alone would justify a 3, but the description adds substantial meaning to 'brief': it may be a free-text musical description, an exact track title, an album, a catalog number, or a composer name, and carries specific rules (preserve the customer's original language, keep durations and exclusions, never add unrequested instruments or vocal restrictions, merge refinements). It also clarifies that discovery searches return at least fifteen candidates, closest first, which gives top_k operational meaning.

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?

The opening states a specific verb and resource — finding existing, licensable music or sound effects from a written brief — and enumerates the domains (ad, trailer, YouTube, podcast, game, film) with the descriptive dimensions (mood, scene, genre, instruments, energy). It explicitly carves out what it is not: not generation, not lyrics, not identification, not playback of commercial releases. The name-lookup branch (track, album, catalog number, composer) further distinguishes it from generic search.

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?

It gives explicit when-to-use ('user needs existing, licensable music') and when-not-to-use ('generate new music, write lyrics, identify a song, or play commercial releases by other artists'). It also handles edge cases with clear rules: refinement calls must merge established requirements with the latest change, retries after a technical failure are user-initiated only, and a name must be passed here before telling a user a track is unavailable.

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