Skip to main content
Glama
romanstark

Ableton Maestro

lom_set

Set an Ableton Live property via LOM path and verify the applied value with read-back, catching clamped, quantized, or ignored writes.

Instructions

Write a property value by LOM path and return verification read-back.

Args:
    path: Settable dotted LOM path.
    value: Value to set, or object reference dict {'__path__': '...'} for object properties.

Returns:
    Dictionary reporting requested, before, after, clamped, and changed status. For a
    device parameter it also carries ``display`` and ``is_quantized``.

Note:
    Live does not accept an out-of-range value silently, however often that is given
    as the reason to read back. Measured 2026-08-30 against Live 12.4.5: it refuses
    them out loud and stores nothing. ``...mixer_device.volume.value = 1.4`` answers
    ``live_error "Invalid value. Check the parameters range with min/max"`` and the
    value stays at 0.85; ``song.tempo = 5000`` answers "Tempo out of range"; a
    panning of 5 is refused the same way.

    What the read-back really catches, measured the same day, is quantised snap:
    ``<Compressor>.parameters[10].value = 0.4`` (Model: Peak / RMS / Expand) stored 0,
    reporting ``before 1, after 0, clamped: true, changed: true, read_back:
    "clamped", display: "Peak", is_quantized: true``. A caller who asks for a value
    between two steps gets a different one and is told nowhere else.

    Two more, measured separately: a write can apply asynchronously, so the first
    read is stale (``read_back: "not_observed"``, which is not ``clamped``), and a
    method call has no read-back at all. Live also ignores an unknown property name
    silently and reports success for a write that did nothing.

    A collection (``song.tracks``, ``device.parameters``) cannot be assigned. Address
    an element and set one of its properties.

    A Live object cannot travel as a plain value, and there are two cases behind
    that. ``song.tracks[0].mixer_device.volume`` is a DeviceParameter and the wanted
    value is one level down, so write ``...volume.value``. But a property whose value
    really is an object (``song.view.selected_track``, ``song.view.selected_scene``,
    ``song.view.detail_clip``, ``browser.hotswap_target``, ``clip.groove``, and on a
    device ``input_routing_type`` and ``input_routing_channel``) is written by passing
    a reference: ``value={"__path__": "song.tracks[2]"}``, resolved through the same
    resolver and guards as a ``lom_call`` argument (protocol §5.4). Handed a plain
    JSON value the first five answer ``not_settable`` (measured 2026-08-29 against
    Live 12.4.5). The two routing properties, a compressor's sidechain source and its
    tap point, take their reference out of
    ``<device>.available_input_routing_types`` and
    ``...available_input_routing_channels``, never a name string, because RoutingType
    carries ``category`` and ``display_name`` read-only and an ``attached_object``
    pointing at the Track (measured 2026-08-30, same Live).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYes
valueYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it discloses many important behaviors: stale read-back, asynchronous writes, silently ignored unknown properties, collections not being assignable, and object-reference restrictions. However, the repeated out-of-range passages contain an internal inconsistency between 'does not accept an out-of-range value silently' and 'sometimes accepts out-of-range values silently,' which lowers reliability.

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

Conciseness2/5

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

The opening sentence is usefully front-loaded, but the description is very long and contains three near-identical paragraphs about out-of-range values and read-back. The duplication, contradictory wording, and garbled terms make it bloated and harder to parse than necessary.

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 complex tool with no annotations and no detailed output schema, the description covers most calling scenarios: scalar writes, object-property writes, routing-type references, collection limitations, stale reads, and failure modes. The main gap is the contradictory out-of-range note, which leaves an agent uncertain about one of the tool's core behavioral guarantees.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description is the only real documentation for path and value. It explains dotted LOM paths, scalar values versus object reference dicts {'__path__': '...'}, and gives concrete examples such as song.view.selected_track and available_input_routing_types. This far exceeds what the bare input schema provides.

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?

The description opens with a specific verb and resource: 'Write a property value by LOM path and return verification read-back.' This clearly distinguishes lom_set from siblings like lom_get and lom_call, and names the write-plus-verification behavior without ambiguity.

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?

The description gives strong context for when to set a scalar property versus an object property, warns that collections cannot be assigned, and explains how object references are resolved through the same mechanism as lom_call. It does not explicitly enumerate alternative tools or state 'use lom_call for method calls,' so it stops short of full exclusion guidance.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/romanstark/ableton-maestro'

If you have feedback or need assistance with the MCP directory API, please join our Discord server