Skip to main content
Glama

generate_arrangement

Creates per-instrument house MIDI files from tempo, key, mode, and arrangement settings, returning written file paths for DAW import.

Instructions

Generate a house MIDI pack (separate .mid per instrument) into out_dir.

bpm: tempo, 60 to 200. root: key root note like 'G','A','C#'. mode: 'minor' or 'major' (sets the i-chord quality; the vamp is i7 + ii-m7 a whole step up). arrangement: 'loop' (8-bar groove) or 'full' (128-bar, 8 sections: intro/groove/breakdown/build/drop/breakdown/groove/outro).

Drums use GM notes (kick=36, clap=39, snare=38, closed hat=42, open hat=46). Pitched parts need a synth per channel. Returns the list of written files.

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": {
      "out_dir": "<out_dir>"
    },
    "name": "generate_arrangement"
  }
}

Input Schema

NameRequiredDescriptionDefault
bpmNo
modeNominor
rootNoG
out_dirYes
arrangementNofull

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose the key side effect (writes separate .mid files into out_dir), the return value ('Returns the list of written files'), and the GM note mapping for drums, but it never says whether existing files are overwritten, whether the directory is created, or what happens on invalid bpm/root values.

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 output artifact is front-loaded in the first sentence and the parameter notes follow in a compact, scannable list. The parenthetical section breakdown and GM note list are dense but each earns its place by removing ambiguity the schema cannot; only the drum note mapping feels marginally optional.

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 five-parameter file-writing tool with no annotations and no output schema, the description covers the essentials: what gets written, where, what is returned, and what downstream setup the generated MIDI requires. The remaining gaps — overwrite semantics and failure modes — are real but secondary for an agent that just needs to call it correctly.

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 schema coverage at 0%, the description compensates well: bpm is bounded 60–200, root is given with concrete examples ('G','A','C#'), mode's two values are explained along with the harmonic consequence (i-chord quality, i7 + ii-m7 vamp), and arrangement's two modes are fully expanded. Only out_dir is left thin — it is named as the target but its preconditions are never described.

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 description opens with a specific verb and concrete artifact: 'Generate a house MIDI pack (separate .mid per instrument) into out_dir.' It states the genre, the file format, the per-instrument granularity, and the destination, which is enough to distinguish it from the sibling tools analyze_song and list_pack without opening any schema.

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?

It gives real decision context for the arrangement parameter ('loop' = 8-bar groove vs 'full' = 128-bar with 8 named sections), which is exactly the choice an agent must make, and flags the prerequisite that 'Pitched parts need a synth per channel.' What it lacks is any explicit when-to-use / when-not guidance relative to alternatives, or whether out_dir must already exist.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools