Skip to main content
Glama

load_device

Destructive

Load a built-in device or preset onto a track or chain in Ableton Live, returning its address and rack macro names. Replaces the track's instrument when loading instrument presets.

Instructions

Load a device or preset onto a track and return its address and, for a rack, its macro names.

Built-in devices go exactly at index. Presets load like a drag from the browser: an instrument replaces the track's instrument (the answer names what it replaced). A file outside the User Library and Packs is refused with a hint to move it into the User Library. Live selects the track it loads onto.

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": {
      "target": "<target>",
      "item": "<item>"
    },
    "name": "load_device"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemYesA built-in device name (Operator, Reverb, CC Control), a path from find_in_library (Instruments/Instrument Rack/Bass/Electric Bass Soft.adg), a preset name, or a file path in the User Library or Packs
indexNoFor built-in devices: position from 0. Empty: at the end.
targetYesTrack (t0, rA, m) or, for built-in devices, a chain

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and non-idempotent, but the description goes further by naming exactly what destruction happens (an instrument replaces the track's existing instrument) and that the response reports the replaced item. It also discloses the refusal behavior for out-of-scope file paths and a set side effect (Live selects the loaded track).

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?

The core action and return value are front-loaded in the first sentence, followed by tight case-specific rules in descending order of importance. No filler or restatement of the tool name.

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?

With no output schema, the description correctly spells out return values and the replacement-report detail, and it covers the main failure mode (disallowed file location). The one remaining gap is that the target/chain address formats in the schema are never explained.

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 coverage is 100%, so all three parameters are already documented. The description adds only a marginal nuance — that index applies specifically to built-in devices, implying presets ignore it — while leaving the opaque target address syntax (t0, rA, m) unelaborated, so baseline-3 with a small lift is fair.

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 (load), two resource types (device or preset), the destination (a track), and even the return payload (address, plus macro names for a rack). An agent can distinguish this from read_device, configure_device, or find_in_library 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?

Gives clear per-case rules: built-in devices take index, presets behave like a browser drag, and files outside the User Library/Packs are refused with a corrective hint. It stops short of explicitly naming the alternative tool that supplies a valid path, so routing to find_in_library is only implied.

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