Live Maestro

Overview Schema Source Related Servers Discussions Admin

capture_audio

Record actual audio at the Analyzer’s position in Ableton Live with a timing witness, optionally cueing a stopped Arrangement from a beat; save the run to an output directory.

Instructions

Record actual audio at the Analyzer's position, with a recorded timing witness.

Requires the updated Analyzer loaded in Live. Main is measured before its fader;
put it at 0 dB when comparing the main output. from_beat temporarily cues/starts
a stopped Arrangement; transport is restored after capture. Without it, record
whatever currently reaches the device. No solo, routing or device parameters change.
Record/cancel status is available through get_audio_job/cancel_audio_job.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`track`	No	Name, index as text, or master/Main.	master
`confirm`	No	True carries the removal out. False changes nothing and returns a report of what the call would remove, which is how to look before committing to it.
`from_beat`	No	Temporarily start a stopped Arrangement at this quarter beat; None records the current signal without changing transport.
`output_dir`	Yes	Parent directory for a unique audio run.
`duration_seconds`	No	Seconds to record after cueing; exported audio also includes pre-roll.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 15, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Goes beyond the annotations (readOnly=false, destructive=false, idempotent=false) by disclosing that no solo, routing, or device parameters change and that transport is restored after capture. It also adds a prerequisite (updated Analyzer) not captured by any structured field. Return-format detail is absent but an output schema exists.

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 is front-loaded in the first sentence, followed by prerequisite, then parameter caveats. It is dense and a few clauses ('recorded timing witness', the main-fader note) are terse, but every sentence carries actionable content.

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?

Covers the mutation's side effects, prerequisites, and transport behavior, and defers status reporting to named siblings. With an output schema present and full param coverage, the remaining gap (no explicit comparison to analyze_audio/compare_audio) is minor.

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

Parameters4/5

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

Schema description coverage is 100%, so baseline is 3, but the description adds real meaning for from_beat (it cues/starts transport, restored afterward) and for the main-level comparison (measured before fader). These extend the parameter docs rather than restate them.

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?

States a specific verb and resource ('Record actual audio at the Analyzer's position'), which reads distinctly from analysis siblings like analyze_audio/compare_audio. The phrase 'with a recorded timing witness' is unexplained jargon that slightly clouds the otherwise clear purpose.

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?

Gives concrete prerequisites ('Requires the updated Analyzer loaded in Live'), setup guidance (put Main at 0 dB for comparison), and a clear when-to-use rule for from_beat ('temporarily cues/starts a stopped Arrangement... Without it, record whatever currently reaches the device'). It also routes status checks to the specific siblings get_audio_job/cancel_audio_job.

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

Deploy Server