Skip to main content
Glama

Make music

make_music

Make new instrumental music beds with Google Lyria on the Gemini API and put them on the shelf. Costs 30 credits per short bed (about 27 seconds) or 60 per longer track, per version, unless the studio is in mock mode. Use estimate_only first and tell the user the price; max_credits refuses a dearer request. Returns track_ids for render_video.

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": {
      "mood": "<mood>",
      "genre": "<genre>",
      "tempo": "<tempo>",
      "length": "<length>"
    },
    "name": "make_music"
  }
}

Input Schema

NameRequiredDescriptionDefault
moodYes
genreYes
notesNoAnything else, in plain words. Never name artists.
tempoYes
lengthYesSeconds. Up to 25 uses the short clip model, which always makes about 27s ($0.04 a version); longer uses Lyria 3.5 ($0.08)
versionsNo
max_creditsNoRefuse (make nothing) if the price in credits is above this
estimate_onlyNoReturn the price without making anything

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say it is a non-read-only, open-world, non-destructive call; the description goes much further by disclosing credit pricing per version and per track length, the mock-mode exception, and the max_credits hard-refusal behavior. It also names the return value (track_ids) and its intended consumer, which the annotations cannot convey.

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

Conciseness4/5

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

The pricing and estimate_only-first guidance is front-loaded and every sentence carries useful information. The phrasing 'put them on the shelf' is slightly vague and the run-on cost sentence could be split, but there is little waste.

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 an 8-parameter generative tool with no output schema, the definition covers cost, refusal semantics, downstream usage, and the returned track_ids. It is nearly complete, though it does not explain what mock mode is or how multiple versions surface in the result.

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

Parameters4/5

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

With only 50% schema coverage, the description compensates well: it explains that cost scales per version and by track length, clarifies the purpose of estimate_only and max_credits, and ties short versus long output to the pricing tiers. Mood, genre, and tempo are left to their enums, and notes gets no mention beyond the schema's own warning.

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 and resource: making new instrumental music beds with Google Lyria via the Gemini API, and placing them on the shelf. It distinguishes itself from siblings by naming the downstream render_video consumer and by implying retrieval belongs to find_music rather than here.

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 clear operational guidance: call estimate_only first and quote the price to the user, and use max_credits to refuse anything dearer. It does not explicitly contrast with find_music or other generation siblings, so it stops short of full when/when-not routing.

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