Skip to main content
Glama

project_undo

Undo recent changes in a REAPER project by specifying the number of steps to revert (1-100) in a single call.

Instructions

Undo the last step, or the last several steps in one call.

Every change made through these tools is its own named undo step ("MCP: "), and a batch call is one step. A tool that runs many commands, like engine_mix, leaves one step per command, labelled "MCP: # > ". Undo just the last 2 or 3 of them with steps, or use project_undo_group to undo the whole run.

Args: steps: How many steps to undo, 1-100 (default 1). Stops early if the undo history runs out. The response lists every step undone, most recent first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stepsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.2
    • addedInput schema / properties / steps
      Added value: +{
      +  "default": 1,
      +  "title": "Steps",
      +  "type": "integer"
      +}
  2. First observedv0.3.0

TDQS

A5/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so richly: it explains named undo steps, batch-call granularity, the engine_mix multi-command labeling pattern, early stop when history is exhausted, and the response ordering. This goes well beyond a generic 'undo' statement.

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?

The description is detailed but every sentence earns its place, and the core action is front-loaded. The undo-step naming and labeling details are necessary context for correct use, not padding.

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

Completeness5/5

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

For a one-parameter tool with no annotations and no output schema, the description covers the parameter semantics, edge behavior, response shape, and sibling alternative. Nothing needed to invoke it correctly is missing.

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

Parameters5/5

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

Schema coverage is 0%, but the description fully compensates: it defines `steps` as a 1-100 count with default 1, states it stops early when history runs out, and notes the response lists each undone step most recent first. This adds real meaning beyond the bare integer 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?

The description states an unambiguous verb+resource: 'Undo the last step, or the last several steps in one call.' It further distinguishes this tool from project_undo_group by explaining the whole-run grouping model, so an agent can tell them apart without inspecting schemas.

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 explicitly explains when to use project_undo vs project_undo_group: undo individual steps with `steps`, or 'use project_undo_group to undo the whole run.' This gives clear selection criteria against an alternative sibling.

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

Deploy Server

Other Tools