Skip to main content
Glama

Fresh

audacity_fresh
Destructive

Resets Audacity to an empty single-window session, backing up existing tracks to an .aup3 file first. Use it to start a clean project safely without opening a second window.

Instructions

Get an empty project in a single window. A running session is backed up when it has tracks (backupTo required), then restarted, even when empty. Restart is Windows-only; on other platforms save and quit Audacity first. Never use the New menu: a second project window has crashed Audacity 3.7 under scripting.

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_fresh"
  }
}

Input Schema

NameRequiredDescriptionDefault
visibleNo
backupToNo.aup3 path for the current project

Output Schema

NameRequiredDescriptionDefault
startedYes
visibleYes
processesYes
backedUpToYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description goes further by explaining what is destroyed (the running session is backed up), what is restarted, and the platform restriction on restart. It does not say what the returned project state looks like, but the output schema covers that.

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?

Three sentences, each carrying distinct operational information: purpose, backup/restart semantics, and a crash-avoidance warning. The most important constraint (single window, never use New) is placed where it will be read, and nothing is redundant.

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 destructive, open-world tool with an output schema and annotations, the description supplies the risky behavior, platform limits, and parameter conditionality an agent needs before calling. The only gap is the unaddressed 'visible' parameter, which neither schema nor prose explains.

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 coverage is only 50% (the 'visible' parameter is undocumented), but the description compensates meaningfully by stating that backupTo becomes required when the running session has tracks — a conditional rule the schema does not express, since backupTo is listed as optional. It still leaves 'visible' unexplained.

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 and outcome: 'Get an empty project in a single window.' That is concrete and distinguishable from sibling tools like audacity_launch or audacity_import, though it never names an alternative tool directly, leaving the differentiation implicit.

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?

It spells out preconditions and exclusions explicitly: back up a running session with tracks (backupTo required), restart is Windows-only, on other platforms save and quit first, and never use the New menu. That is a full when/when-not/alternative-discipline statement with a documented hazard behind it.

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