Skip to main content
Glama

undo

Revert the last 1–50 changes in Ableton Live, including grouped and batch edits, to restore a previous set state.

Instructions

Undo the last change(s) in Live, like Cmd/Ctrl+Z. Each tool call that changed the set is one step; tools that make many changes at once (drum patterns, progressions, arrangements, MIDI imports…) are one step too, as is everything between start_undo_group and end_undo_group. It is Live's own Undo: if the user edited the set meanwhile, their change comes first.

Parameters:

  • steps: How many steps to undo (1–50)

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": "undo"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations present, the description carries the full burden and does well: it discloses the mutation semantics, the step-counting model, grouping behavior, and that this is Live's own undo stack shared with the user. It omits failure/no-op behavior and says nothing about whether the undo itself can be reversed (redo), which matters for a destructive-feeling operation.

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 core analogy ('like Cmd/Ctrl+Z') is front-loaded in the first clause, followed by the step-counting rules and the user-edit caveat, then a compact parameter line. Every sentence adds information and nothing is 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?

An output schema exists, so return values need not be explained, and with a single optional parameter the description covers all the reasoning an agent needs to pick a step count. The only gap is edge-case behavior when the undo stack is empty or exhausted by the requested step count.

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 0% — the 'steps' property has no description, no minimum, and no maximum — so the description does the work by defining it as 'How many steps to undo (1–50)'. That range constraint is real meaning not present in the schema. It could add what the default (1) means in practice, but the core semantics are covered.

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 effect — 'Undo the last change(s) in Live, like Cmd/Ctrl+Z' — which is unambiguous for an agent. It distinguishes itself from the undo-grouping siblings by explaining that everything between start_undo_group and end_undo_group counts as one step, but it does not explicitly frame those siblings as alternatives to choose between, keeping it just short of a 5.

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 clear operational context: one tool call equals one step, batch tools equal one step, and grouped ranges equal one step, so the agent can predict exactly how far back a call will go. It also warns that a user's intervening edit takes precedence over the agent's. It never states when-not to use it (e.g., vs. a delete/recreate flow) or what happens when there is nothing left to undo.

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