Skip to main content
Glama

Pipeline

audacity_pipeline
Destructive

Previews or runs a reviewed cleanup and mastering chain on a single Audacity track, listing exact commands in dry-run mode before applying presets, noise reduction, normalization, and limiting.

Instructions

Preview or run a reviewed cleanup/mastering chain on one track: voice, podcast, interview, audiobook, vocal, live, music, lo-fi or cleanup. dryRun lists exact ordered commands without changing selection. Noise reduction requires supplied room tone; normalization and limiting are explicit. Default range is the track extent, recalculated after edits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "track": "<track>"
    },
    "name": "audacity_pipeline"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
lufsNo
ratioNo
rmsDbNo
startNo
trackYes
bassDbNo
dryRunNo
peakDbNo
presetNovoice
attackMsNo
compressNo
loudnessNonormalization can raise quiet audio; select it explicitlynone
removeDcNo
trebleDbNo
lowPassHzNo
releaseMsNo
highPassHzNo
limitPeakDbNooptional limiter after normalization; measure the result
thresholdDbNo
noiseProfileNoexplicit room-tone interval; omitting it skips noise reduction
removeClicksNomust remain false: native Click Removal can open a blocking result dialog
shortenPausesNooptional destructive silence truncation; changes timing and video sync

Output Schema

NameRequiredDescriptionDefault
notesYes
stepsYes
dryRunYes
presetYes
appliedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the mutation profile is covered; the description adds value beyond that by explaining the dryRun preview semantics and that the default range 'is the track extent, recalculated after edits', which is non-obvious state behavior an agent could otherwise get wrong. It also discloses that normalization/limiting are opt-in rather than automatic, reducing risk of unexpected loudness changes. It does not discuss undo or the schema's warning about Click Removal opening a blocking dialog, which stays hidden in the parameter docs.

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?

Four short sentences, front-loaded with the core action and immediately followed by the safety-relevant dryRun behavior and the hard preconditions. There is essentially no filler; the only ambiguity is the 'lo-fi' vs schema 'lofi' spelling, which costs a little precision without adding bulk.

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

Completeness3/5

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

For a destructive, 23-parameter chain tool, the description establishes the essential contract: preview vs commit, preset families, required room tone, explicit normalization, and default range behavior. An output schema exists, so return values need not be described. However, with 22% schema coverage, many DSP parameters and the destructive silence-truncation option (shortenPauses) are left for the agent to discover from bounds and defaults alone, so completeness is adequate but not sufficient for confident invocation.

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

Parameters2/5

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

Schema description coverage is only 22% across 23 parameters, so the description must carry substantial explanatory load, and it covers only a handful: preset (full enum listed, though it writes 'lo-fi' where the schema enum is 'lofi'), dryRun, noiseProfile (room-tone requirement), start/end (default range), and by implication loudness/limitPeakDb. The many DSP knobs - lufs, rmsDb, peakDb, ratio, thresholdDb, attackMs, releaseMs, bassDb, trebleDb, highPassHz, lowPassHz, removeDc, compress, shortenPauses - get no meaning from the description beyond their names and numeric bounds. That is a large gap for a 23-parameter tool.

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 specific verb pair and resource: 'Preview or run a reviewed cleanup/mastering chain on one track.' It enumerates the preset categories (voice, podcast, interview, audiobook, vocal, live, music, lo-fi, cleanup), which tells an agent exactly what kinds of processing this tool encapsulates. It stops short of differentiating itself from sibling effect/macro tools such as audacity_effect or audacity_macros, so it is clear but not sibling-aware.

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?

It gives implied usage guidance by contrasting 'Preview or run' and explaining that 'dryRun lists exact ordered commands without changing selection', which tells an agent how to safely inspect before committing. It also states preconditions for specific stages ('Noise reduction requires supplied room tone; normalization and limiting are explicit'), effectively saying omitting a parameter skips that stage. What is missing is when to choose this over a single-effect or macro tool, and there is no explicit when-not guidance.

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