Skip to main content
Glama

app

Control Ableton Live's interface and state: inspect selection, select tracks, clips, devices or parameters, arrange views, show status messages, and preview browser items without loading them.

Instructions

Live's own interface and state.

info: Live version, CPU load, open dialogs (read only: Tonable never presses a dialog button) and what is selected, as Tonable addresses. select: select a track, scene, clip, device or parameter so the user sees it in Live. show_view, hide_view, focus_view, toggle_browse, scroll_view, zoom_view: arrange Live's windows. set_view: follow_song and draw_mode. show_message: a status-bar message. preview and stop_preview: audition a browser item (a sound or preset) without loading it. Selection and view changes are not undo steps.

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": "app"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemNoFor preview: a path from find_in_library, or a unique name or file.
viewNoFor the view actions: Browser, Arranger, Session, Detail, Detail/Clip or Detail/DeviceChain.
actionYesWhat to do; see the tool description.
targetNoFor select: t0, rA, m (track), s2 (scene), t0/s2 or t0/a1 (clip), t0/d1 (device) or t0/d1:Release (parameter).
messageNoFor show_message: the text for Live's status bar.
refreshNoFor preview: true to walk Live's browser again first.
modifierNoFor scroll_view and zoom_view: true to hold the modifier key.
directionNoFor scroll_view and zoom_view: up, down, left or right.
draw_modeNoFor set_view: Draw mode on or off. Empty: unchanged.
follow_songNoFor set_view: true / false. Empty: unchanged.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds genuinely new behavioral context: dialogs are read-only and never pressed, and selection/view changes are not undo steps. That is exactly the kind of state-mutation nuance annotations cannot express, though it does not cover error behavior or what 'info' returns.

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 with the overall purpose, then a compact per-action list with no filler sentences. The telegraphic style ('set_view: follow_song and draw_mode') is efficient, though a few entries are terse enough to require the schema to decode.

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 12-action, 10-parameter tool with no output schema, the description accounts for every action and flags the non-undo side effect. It stops short of describing return values for 'info' or failure modes, but the coverage is solid for the tool's complexity.

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 documents item, view, target, message, direction, modifier, draw_mode and follow_song. The description adds only marginal meaning beyond that (preview takes a path from find_in_library, target uses Tonable addressing), so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific framing ('Live's own interface and state') and then enumerates each action with a concrete verb+resource: select a track/scene/clip/device/parameter, arrange windows, audition a browser item. It is clear what the tool does, though the multi-action grab-bag nature means no single purpose dominates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Each action gets a short gloss, which implies when to use it (e.g. preview to audition without loading), but there is no explicit when-not guidance and no routing to siblings such as live_status or transport that plausibly overlap with 'info' and view control.

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