Skip to main content
Glama

Measure

audacity_measure

Measure tracks, time ranges, or the current selection in Audacity to get peak, RMS, DC, crest, silence, and defect reports, with optional LUFS/true-peak analysis and target checks.

Instructions

Measure tracks, a time range, or currentSelection using a temporary export; restores selection and preserves track controls. Reports peak/RMS/DC/crest, advisory defects and silence. Optional ffmpeg adds integrated LUFS/LRA/true peak. Reads rendered gain/mute/solo/envelopes, so use file measurement for unprocessed source levels. With targets, returns {measurement,targetCheck}; otherwise returns the measurement directly.

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": "audacity_measure"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
startNo
trackNo
backendNoauto
targetsNo
dualMonoNo
timeoutMsNo
trackCountNo
currentSelectionNo

Output Schema

NameRequiredDescriptionDefault
rmsNo
fileNo
peakNo
notesNo
scopeNo
framesNo
backendNo
crestDbNo
rmsDbfsNo
channelsNo
dcOffsetNo
dualMonoNo
durationNo
peakDbfsNo
perChannelNo
sampleRateNo
measurementNo
silenceGapsNo
targetCheckNo
unavailableNo
truePeakDbtpNo
clippedSamplesNo
integratedLufsNo
discontinuitiesNo
loudnessRangeLuNo
silenceGapCountNo
quietRmsDbfsEstimateNo
dynamicRangeDbEstimateNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations, it discloses the mechanism (temporary export), that selection is restored and track controls preserved, that measurements reflect rendered gain/mute/solo/envelopes, and that ffmpeg is an optional add-on for LUFS. That is real behavioral context that explains why readOnlyHint is false despite being an analysis tool. It does not discuss cost/latency beyond the presence of timeoutMs, which would have completed the picture.

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?

Front-loaded with scope and mechanism, then routing guidance, then return-shape note — a logical order with no filler. Some clauses are telegraphic ('Reports peak/RMS/DC/crest, advisory defects and silence'), but density here is useful rather than padded.

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 nine-parameter tool with nested target objects it covers mechanism, side effects, metric set, backend choice, and both return shapes; an output schema exists so enumerating return fields is unnecessary. The residual gaps are the unexplained secondary parameters (dualMono, trackCount, timeoutMs) rather than anything about core usage.

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 description coverage is 0%, so the description carries the burden and only partly does: it explains the track/start-end/currentSelection scoping, what backend 'ffmpeg' adds, and that targets produce a targetCheck. It leaves dualMono, trackCount, and timeoutMs unaddressed, and never explains that the targets sub-fields are min/max thresholds per metric, which is the most intricate part of the schema.

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?

States a specific verb and multiple scopes (tracks, a time range, or currentSelection) and explicitly names the sibling operation it is not ('use file measurement for unprocessed source levels'). An agent can distinguish it from audacity_measure_file without opening either schema.

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?

Gives a clear routing rule with an alternative: this tool measures rendered gain/mute/solo/envelope-affected audio, so unprocessed source levels should go through file measurement. It also states the optional ffmpeg backend condition for LUFS/LRA/true peak. It stops short of saying when to prefer currentSelection over explicit start/end, but the alternative-selection guidance is explicit.

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