Skip to main content
Glama

Undo a change

drive_undo

Undo recorded Proton Drive batches by restoring or moving items back with per-ID checks; changed items are skipped, and nothing is overwritten.

Instructions

Undo a recorded batch (drive_cleanup, drive_bulk_trash, drive_trash, drive_bulk_move, drive_move, drive_rename): restores or moves items back, each checked by id; nothing is overwritten, changed items are skipped with a reason. action list (newest 20, no names), plan (default), apply (always asks the user first). Needs the local undo record (PROTON_DRIVE_UNDO=0 turns it off).

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": "drive_undo"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoUndo code like K7Q2-M9XD (default: newest batch not yet undone).
actionNoDefault plan.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.12.0

TDQS

A4.5/5.0
Behavior5/5

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

With only destructiveHint=false in annotations, the description adds substantial behavioral detail: id-checked restoration, no overwrites, changed items skipped with a reason, list output limited to newest 20 without names, plan as default, apply requiring confirmation, and the need for a local undo record (with env var to disable).

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?

The description is dense but front-loaded with the core purpose, then supplies important operational details. It could be more structured for readability, but every sentence contributes relevant information without padding.

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 tool with no output schema and two simple parameters, the description covers the essential behavior, safety constraints, action modes, and prerequisites. It does not describe what plan or apply return in detail, but the action list output is briefly characterized.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema for the action parameter by explaining what list, plan, and apply do and how apply behaves. It also reinforces that each item is checked by id, though the id format is already in 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?

The description states a specific verb and resource: undo a recorded batch, and it enumerates the operations whose batches can be undone (drive_cleanup, drive_bulk_trash, etc.). This clearly distinguishes it from the direct operation siblings like drive_trash or drive_move.

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?

The description explains that this tool is for undoing recorded batches from the listed operations and describes the action modes (list, plan, apply) with apply always asking the user first. It does not explicitly state when not to use it or name alternative tools, but the context is clear.

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