Skip to main content
Glama

arrangement

Destructive

Edit Ableton Live timeline clips, scenes, locators, and take lanes by listing, placing, copying, moving, creating, or deleting items.

Instructions

Work on the Arrangement timeline.

list: clips per track, locators, loop. place_scene: copy every clip of a Session scene to the timeline at a bar, in one undo step (envelopes come along as track automation). copy_clip: one Session or timeline clip to a bar. move_clip: a timeline clip (t0/a1) to another bar. create_clip: a MIDI clip on the timeline with notes (audio: create_audio_clip). delete_clip: by track, start and name. add_take_lane. add_locator, rename_locator, delete_locator. list shows each clip's address, type and the take lanes. Times answer as bar|beat ("17|1") and beats. Live cannot read Arrangement automation back.

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": {
      "action": "<action>"
    },
    "name": "arrangement"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipNoFor copy_clip and move_clip: a clip address instead of track and slot: t0/s2 (Session) or t0/a1 (a timeline clip from action list).
nameNoClip or locator name; for delete_clip the clip's name as a check.
slotNoFor copy_clip: the Session slot to copy, from 0.
notesNoFor create_clip: notes, as in write_clip.
sceneNoFor place_scene: scene number from 0 or its exact name.
trackNoFor copy_clip, create_clip, delete_clip, add_take_lane: t0, t1...
actionYesWhat to do; see the tool description.
at_barNoWhere: bar number from 1, as Live shows it (17 = bar 17).
locatorNoFor rename_locator, delete_locator: the locator's name.
at_beatsNoWhere, in beats from the start, instead of at_bar.
length_beatsNoFor create_clip: length in beats. Empty: fit the notes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructive=true, idempotent=false, readOnly=false, so the safety profile is known. The description adds genuinely new behavior: place_scene collapses into "one undo step" with envelopes carried as track automation, and "Live cannot read Arrangement automation back" is an important limitation. It stops short of stating permission requirements or whether delete_clip is recoverable.

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-loaded summary sentence followed by tight per-action clauses; nearly every line carries actionable information. A few items are unabbreviated fragments (bare "add_take_lane.") that cost clarity without saving much space.

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 10-action, 11-parameter mutation tool with no output schema, the description covers most actions, the list return shape ("address, type and the take lanes"), and the undo/automation caveats. The gap is add_take_lane, which is named with no explanation of what it does or which parameters it consumes.

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 schema already explains clip, slot, scene, track, at_bar, at_beats, notes and length_beats. The description adds only the response time format (bar|beat like "17|1" and beats) and reinforces the t0/s2 vs t0/a1 address form; per-action parameter mapping (which param each action needs) is left to the schema.

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?

Opens with a specific resource ("Arrangement timeline") and then enumerates all ten actions with their concrete effects, e.g. "place_scene: copy every clip of a Session scene to the timeline at a bar". It actively distinguishes itself from siblings by routing audio clip creation to create_audio_clip and noting the clip-address format shared with list output.

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 context for choosing between its own actions (copy_clip vs move_clip vs place_scene) and explicitly names create_audio_clip as the alternative for audio clips. It does not, however, say when to prefer this tool over siblings like update_clip, read_clip, write_clip, or scene, leaving that boundary implicit.

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