Skip to main content
Glama
romanstark

Ableton Maestro

read_clip_notes

Inspect MIDI notes in an Ableton Live Session clip: read notes, query a beat window, or count notes without transferring large data.

Instructions

Read MIDI notes of a Session clip, query a specific window, or count notes.

Args:
    track: Track index in song.tracks.
    slot: Scene/slot index in track.clip_slots.
    from_time: Start beat of window to query. Omit to query from beat 0.
    time_span: Window length in beats. Omit to query to the end of the clip.
    count_only: When True, returns note count without transferring note data.
    check: When True, performs validation checks on queried notes.

Returns:
    Dictionary containing notes, count, window parameters, and validation report.

Note:
    Times and positions are expressed in clip-local beats. Muted notes are included
    and carry ``mute: true``. ``time_span`` is a length in beats, not an end beat:
    beats 24 to 32 is ``from_time=24, time_span=8``.

    Windowing and counting exist because there was otherwise no way to ask a small
    question. Measured 2026-08-30: surveying note density across 59 drum clips meant
    reading every note of every clip, and one clip alone came back as 384 notes and
    57k characters, past the tool-result cap, so it spilled to a file. The LOM has no
    ``note_count`` on ``Clip`` at all, so counting meant transferring everything in
    order to measure it. ``count_only=True`` counts inside Live and carries back one
    integer.

    With ``count_only`` there is nothing to validate, so ``check`` is ignored. With a
    window, ``check`` sees the window and not the clip.

    Returned notes are sorted by time, then pitch. Live hands its notes back ordered
    by pitch, which is the one order a musical instruction never means: "the third
    note", "every other note" and "the last note" are all about when a note sounds.
    Measured 2026-08-30 against Live 12.4.5: four notes written at beats 0, 1, 2, 3
    with pitches 72, 60, 67, 62 came back 60, 62, 67, 72, so taking every other entry
    off the raw list picks alternating pitches rather than alternating beats, silently
    and plausibly. For Live's own order call ``get_notes_extended`` through
    ``lom_call``.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slotYes
checkNo
trackYes
from_timeNo
time_spanNo
count_onlyNo

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

A5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden, and it delivers extensively: muted notes are included and marked, times are clip-local beats, time_span is a length not an end beat, and returned notes are sorted by time then pitch. It also documents Live's surprising pitch-first ordering with a dated measured example, which is exactly the kind of behavioral disclosure an agent cannot infer from the schema.

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 description is long but structured with Args, Returns, and Note sections, and the core purpose is front-loaded. The extended Live ordering anecdote is verbose but earns its place by documenting a subtle, plausible bug that could silently corrupt musical interpretation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six parameters, no schema descriptions, no annotations, and subtle runtime behavior, the description is complete: every parameter is semantically covered, return contents are summarized, edge cases are disclosed, and the alternative for Live-native ordering is provided. Nothing required to call the tool correctly is missing.

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%, but the description compensates fully. Each parameter is explained beyond its type: track and slot get index semantics, from_time/time_span get omit behavior and beat units, and count_only/check get precise behavioral meaning including ignored cases.

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: 'Read MIDI notes of a Session clip, query a specific window, or count notes.' It clearly distinguishes this from sibling tools like write_clip_notes and read_automation, and even names get_notes_extended when contrasting ordering behavior.

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?

The description explains when windowing and counting are appropriate ('no way to ask a small question'), clarifies the semantics of check with and without a window or count_only, and explicitly directs users to get_notes_extended via lom_call when Live's native note order is desired. This gives an agent concrete decision rules rather than leaving usage to inference.

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