Skip to main content
Glama

generate_music

Idempotent

COSTS CREDITS from the user's wallet. State the price (from estimate_credits) and get the user's confirmation before calling. Generates a song, a sound effect (type "sound_effect") or a spoken voice-over with music (type "speech"). Returns immediately with a generationId; poll get_generation for results.

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": {
      "model": "<model>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "generate_music"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoFor song and speech: simple = describe it; custom = write the lyrics / exact script yourself. Not needed for type sound_effect (mode "sound_effect" without type is also accepted).
typeNosong = a song with music; sound_effect = a short sound effect / loop; speech = spoken voice-over / narration with optional background music (not singing). See list_models[].types.song
modelYesModel id from list_models (e.g. "suno", "acestep").
paramsNoParameters for the chosen type + mode: list_models[].params[mode] for songs, list_models[].params.sound_effect for sound effects, list_models[].speech.params[mode] for speech. Unknown keys are rejected.
versionNoVersion id from list_models; omit for the model's default version.
idempotencyKeyYes8-64 chars [A-Za-z0-9._:-]. Stable per logical request: resend the same key + same params after a timeout to get the existing result instead of paying twice. Use a new key when anything changes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / mode / description
      Previous value: -"simple = describe the song; custom = write lyrics/style yourself; sound_effect = a short sound effect / loop instead of a song. See list_models[].modes."New value: +"For song and speech: simple = describe it; custom = write the lyrics / exact script yourself. Not needed for type sound_effect (mode \"sound_effect\" without type is also accepted)."
    • changedInput schema / properties / params / description
      Previous value: -"Mode-specific parameters; schema in list_models[].params[mode]. Unknown keys are rejected."New value: +"Parameters for the chosen type + mode: list_models[].params[mode] for songs, list_models[].params.sound_effect for sound effects, list_models[].speech.params[mode] for speech. Unknown keys are rejected."
    • addedInput schema / properties / type
      Added value: +{
      +  "default": "song",
      +  "description": "song = a song with music; sound_effect = a short sound effect / loop; speech = spoken voice-over / narration with optional background music (not singing). See list_models[].types.",
      +  "enum": [
      +    "song",
      +    "sound_effect",
      +    "speech"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "model",
      -  "mode",
      -  "idempotencyKey"
      -]New value: +[
      +  "model",
      +  "idempotencyKey"
      +]
  2. First observed

TDQS

A4/5.0
Behavior3/5

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

Adds real value beyond the annotations: it charges credits from a wallet, and it is asynchronous, returning only a generationId. The annotations already cover idempotency and non-destructiveness, so the incremental disclosure is the billing cost and the async contract.

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

Conciseness5/5

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

Three sentences, front-loaded with the cost warning, then the capability, then the return/polling contract. Zero filler.

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 six-parameter, nested-schema generation tool with no output schema, it covers the cost prerequisite, the async return handle, and the follow-up poll. It omits failure behavior, expected latency, and what invalid model/version errors look like, which leaves minor gaps.

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

Parameters3/5

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 mostly restates the type values the schema already documents with examples. It does clarify that mode is not needed for sound_effect, but the nested params object is still delegated to list_models rather than explained here.

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?

States a specific verb (generates) plus the three resource kinds (song, sound effect, spoken voice-over) and ties each to its type value. An agent can immediately tell this apart from sibling readers like list_songs or check_account.

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?

Gives an explicit pre-call workflow (get price from estimate_credits, state it, get confirmation) and an explicit post-call workflow (poll get_generation). It never states when NOT to use it — e.g. that it cannot modify an existing track — so it is strong context without full exclusion guidance.

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.