Skip to main content
Glama
romanstark

Ableton Maestro

describe

Explore live Ableton objects at runtime by path to reveal class, properties, children, and methods. Survey device parameters when needed to diagnose unconfigured plug-ins.

Instructions

Introspect any live object: class, properties, children, and methods.

This is the route to the dynamic surface: what a loaded plug-in actually exposes,
which no catalog can know in advance because it is decided at runtime and, for
third-party plug-ins, by what the user picked up in Configure mode.

Args:
    path: a LOM path, e.g. ``song``, ``song.tracks[0]``,
        ``song.tracks[0].devices[1]``. Look shapes up in ``ableton://catalog``.
    depth: how far to descend. Deep describes over a whole set can be slow
        and the cost is unmeasured.
    with_parameters: for a device path, survey every parameter (name, value,
        min/max, quantized steps, display unit) instead of just the child
        counts, and diagnose an unconfigured plug-in rather than returning a
        useless one-entry list.

Methods are never callable through a path. Use ``lom_call``, and only names on the
script's own allowlist.

Measured caveat (Live 12.4.5): the parameter survey depends on
``lom_describe`` reporting a ``count`` for the ``parameters`` child, and a
Live ``Vector`` that refuses ``len()`` reports none, so the survey comes back
with zero parameters on a device that has them. When that happens this tool falls
back to probing parameter indices, reports the names it found, and says which
of the two answers you are looking at.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYes
depthNo
with_parametersNo

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

A4.6/5.0
Behavior5/5

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

With zero annotations, the description carries the full disclosure burden and meets it: it states the Live 12.4.5 version requirement, the precondition that the connected set be loaded, that rack display is not implemented, that deep describes are slow with unmeasured cost, and that the tool falls back to probing parameter indices and reports which of two answer kinds it is returning. All of this is behavior beyond what the schema could convey.

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?

Purpose statement is front-loaded, followed by context, a clean Args block, then behavioral constraints — a good scan order for an agent. It is long, but every sentence carries information an agent needs. The final paragraph is structurally garbled ('Live 12.4.5. When that happens this tool falls back...') and appears to belong with the with_parameters explanation, which hurts scannability.

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 runtime-introspection tool with 3 parameters, no annotations, and an output schema, the description is nearly complete: purpose, all parameter semantics, performance risk, version/platform preconditions, fallback behavior, and routing to lom_call/lom_enums/browser. Notable gaps are the lack of any distinction from the lom_describe sibling and no statement of error behavior for invalid paths, though the presence of an output schema relaxes the need to describe return values.

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% and the schema provides no parameter help, so the description must compensate fully. It does: path gets concrete LOM examples (song.tracks[0].devices[1]) plus a pointer to ableton://catalog, depth gets a cost caveat, and with_parameters gets its complete effect (name, value, min/max, quantized steps, display unit) and its diagnostic purpose.

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?

Opens with a specific verb and resource: 'Introspect any live object: class, properties, children, and methods,' which enumerates the exact outputs and separates it from get_* tools, lom_get, and lom_call. However, it never addresses the near-identically-named sibling lom_describe, so an agent cannot tell whether describe is an alias, a wrapper, or a distinct operation.

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

Usage Guidelines5/5

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

Explicitly states when this tool is the right choice ('the route to the dynamic surface...which no catalog can know in advance') and gives direct when-not guidance with named alternatives: 'Methods are never callable through a path. Use lom_call' and 'call lom_enums for rack.lom_parameters and browser for presets.' It also tells when to set with_parameters (diagnose an unconfigured plug-in).

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