Skip to main content
Glama

update_set

Change selected Ableton Live Set settings—tempo, time signature, loop, key, recording, groove, Link, and track-arming rules—while leaving unspecified fields untouched; revert with one undo step.

Instructions

Change the Set's tempo, time signature, Arrangement loop, metronome, key, recording state (record, overdub, session record, punch, quantization), groove amount, Link and track-arming rules.

Only the fields you give change; the answer shows the Set's state afterwards, with one result line for each recording or behavior field (Live keeps the old value for a setting it refuses, and the line says so). One undo step.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "update_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
linkNoAbleton Link on or off: true / false.
loopNoArrangement loop on or off: true / false. Empty: unchanged.
scaleNoScale name as Live shows it: Major, Minor, Dorian...
tempoNoBPM, e.g. 92. Empty: unchanged.
recordNoArrangement record on or off: true / false.
overdubNoArrangement overdub on or off: true / false.
punch_inNoPunch in: true / false.
metronomeNotrue / false. Empty: unchanged.
punch_outNoPunch out: true / false.
root_noteNoKey root for Live's scale mode: C, F#, Bb. Empty: unchanged.
scale_modeNoHighlight scale notes in the MIDI editor: true / false.
swing_amountNoSwing amount 0-1 (older global swing).
exclusive_armNoArming one track disarms the others: true / false.
groove_amountNoGlobal groove amount, 0 = off, 1 = 100 %.
automation_armNoAutomation arm (session automation record).
exclusive_soloNoSoloing one track unsolos the others: true / false.
session_recordNoSession record on or off: true / false.
time_signatureNoe.g. 4/4, 3/4, 6/8. Empty: unchanged.
loop_start_beatsNoLoop start in beats. Empty: unchanged.
select_on_launchNoSelect a clip when it is launched: true / false.
loop_length_beatsNoLoop length in beats (16 = four 4/4 bars).
link_start_stop_syncNoLink start/stop sync: true / false.
clip_trigger_quantizationNoGlobal launch quantization: None, 8 Bars, 4 Bars, 2 Bars, 1 Bar, 1/2, 1/2T, 1/4, 1/4T, 1/8, 1/8T, 1/16, 1/16T, 1/32.
midi_recording_quantizationNoRecord quantization: None, 1/4, 1/8, 1/8T, 1/8 + 1/8T, 1/16, 1/16T, 1/16 + 1/16T, 1/32.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A3.7/5.0
Behavior4/5

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

With annotations already declaring readOnlyHint=false, destructiveHint=false and idempotentHint=false, the description still adds real behavior: the response echoes the Set's post-change state, one result line is emitted per recording/behavior field, refused settings keep their old value with an explanatory line, and the whole call is a single undo step. The last point is especially valuable for a mutation tool with idempotentHint=false. It does not warn about side effects of arm/record flags or state preconditions, which keeps it below a 5.

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?

The first sentence front-loads a scannable enumeration of what can be changed, and the second and third sentences cover mutation and reply semantics without padding. The field list partly duplicates what the schema already enumerates, so it is slightly longer than strictly necessary, but the ordering is logical and nothing is wasted prose.

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 24-parameter, all-optional mutation tool with no output schema, the description covers the essentials: partial-update contract, response shape, per-field failure reporting, and undo cost. Missing only guidance on precedence when interdependent fields are sent together (e.g. session_record vs record, link vs link_start_stop_sync), which is a real gap for a tool this broad but not fatal.

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 24 parameters already carry their own descriptions including formats and valid values. The description contributes only a thematic grouping of those fields and the empty-string-means-unchanged convention is already in the schema. Baseline 3 is appropriate since the schema does the heavy lifting.

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 concrete verb and resource ('Change the Set's...') and enumerates the specific domains affected: tempo, time signature, loop, metronome, key, recording state, groove, Link and arming rules. That is far more specific than restating the name. It stops short of naming the read-only counterpart (read_set) or transport siblings, so the agent must infer the boundary itself.

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

Usage Guidelines3/5

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

'Only the fields you give change' establishes partial-update semantics, which implicitly tells the agent this is for sparse edits rather than full state writes. However there is no explicit when-to-use versus read_set or the transport/arrangement tools, and no stated prerequisites for enabling record, punch, or session record.

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