Skip to main content
Glama

transport

Control Ableton Live playback and clip/scene triggering, stop clips or tracks, jump to locators or beats, tap tempo, capture MIDI, record sessions, and re-enable automation.

Instructions

Play, stop or continue; launch a clip (fire_clip track+slot, also records into an empty slot of an armed track) or a scene (fire_scene); stop one clip (stop_clip), one track's clips (stop_track) or all clips; jump to a time in beats (jump), by a distance (jump_by), to a locator, or to the next or previous locator; jump_in_clip inside the clip a track is playing; play_selection; tap_tempo; capture_midi (keep what was just played); trigger_session_record; back_to_arranger (leave Session playback); re_enable_automation after a parameter was moved by hand or by set_device_params.

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": "transport"
  }
}

Input Schema

NameRequiredDescriptionDefault
slotNoFor fire_clip and stop_clip: the slot (scene row) from 0.
sceneNoFor fire_scene: scene number from 0 or its exact name.
trackNoFor fire_clip, stop_clip, stop_track, jump_in_clip: t0, t1...
actionYesWhat to do; see the tool description.
locatorNoFor jump: a locator name instead of time_beats.
time_beatsNoFor jump: song position in beats. For jump_by: beats to move (negative goes back). For jump_in_clip: beats to jump inside the playing clip.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare the generic profile (not read-only, not destructive, not idempotent), so the description carries real weight — and it delivers: fire_clip 'also records into an empty slot of an armed track' is a non-obvious side effect, and back_to_arranger/re_enable_automation explain state transitions an agent could not infer. It still omits error and prerequisite behavior (what happens firing an unarmed track, whether play resumes from the last position).

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

Conciseness5/5

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

Score adjusted to 3: the content is a single semicolon-chained sentence fragment that is dense and hard to scan for a 19-action dispatcher; an action-per-line list would serve an agent better. The opening play/stop/continue is correctly front-loaded and little wording is truly redundant, which saves it from a lower mark.

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 19-action, 6-parameter mutation dispatcher with no output schema, the description covers every action and the cross-action semantics (armed-track recording, automations re-enabled). What remains missing — return shape per action, failure modes, and prerequisite state like an armed track — is modest given full schema coverage and supplied annotations.

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 slot, scene, track, locator, and time_beats, including which action each applies to. The description's 'fire_clip track+slot' and 'jump_in_clip inside the clip a track is playing' largely restate that mapping rather than adding format or constraint detail. Baseline 3 is appropriate.

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 verb set (play/stop/continue, launch clip or scene, jump, record) over a clearly bounded resource domain — transport and Session playback control. An agent can tell this is the Live transport dispatcher without opening the schema. It does not, however, differentiate itself from siblings such as 'scene' or 'arrangement', which could plausibly overlap with fire_scene or locator-based jumps.

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?

Each of the 19 enum actions is paired with a short usage gloss: 'capture_midi (keep what was just played)', 'back_to_arranger (leave Session playback)', 're_enable_automation after a parameter was moved by hand or by set_device_params'. That last clause even routes the agent from a sibling workflow into this action. There are no explicit when-not rules or pointers to alternative tools for related needs (e.g., reading clip content), which keeps it below a 5.

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