Skip to main content
Glama

write_midi_file

Export notes to a .mid file for drag-and-drop into Ableton Live without Live running; avoid overwriting existing files by choosing a new name.

Instructions

Save notes as a .mid file in ~/Music/ableton-mcp/midi/ without using Live (works even when Live is closed). The user can drag the file into Live. The file holds notes only, so tell the user to drop it on a track that has an instrument (e.g. a Drum Rack kit) or it plays silent. Times are in beats. name: letters, digits, space, '_' or '-'. An existing file with that name is never overwritten: pick a new name.

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": {
      "name": "<name>",
      "notes": "<notes>"
    },
    "name": "write_midi_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
bpmNo
nameYes
notesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A4.1/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: the write target is the filesystem rather than the Live set, no Live connection is required, and an existing file with the same name is never overwritten (so the agent must pick a new name). Annotations already cover the read-only/destructive profile, and the description adds the important no-overwrite safety rule, though it omits what happens on invalid names or whether directories are created.

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?

Front-loads the action and location, then adds the drag-into-Live guidance and naming constraints. Slightly dense with several distinct points in one paragraph, but each sentence carries actionable information with no padding.

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?

No output schema exists, so the description should ideally state what is returned (e.g., the file path), which it does not. Otherwise it covers the essential context — offline operation, file location, manual import step, instrument requirement, and no-overwrite policy — well enough for correct invocation.

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 0%, so the description must compensate. It does constrain the 'name' parameter (letters, digits, space, '_' or '-') and specifies that times are in beats, which is valuable. However, the 'notes' object fields (pitch, duration, velocity) and especially 'bpm' are left entirely undocumented in both schema and description.

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 ('Save notes as a .mid file') plus the exact output location (~/Music/ableton-mcp/midi/) and the key differentiator 'without using Live'. This cleanly separates it from Live-dependent siblings like write_notes and create_midi_clip.

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 when-to-use context: works when Live is closed, and the user drags the file into Live afterward, including the instruction to warn about needing an instrument on the target track. It does not explicitly name sibling alternatives (write_notes, create_midi_clip) to route between them, so it falls 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.