Skip to main content
Glama
CLO Atelier

CLO Atelier

by benproj

Undo changes

clo_undo

Undo one or more project-changing tool calls by restoring patterns, seams, fabrics, colorways, and 3D drape to their prior state. Manual CLO edits since that point are discarded; redo recovers them.

Instructions

Undo the last tool call that changed the project, or several, by restoring the garment as it was before. Works for everything the tools change, including simulation, moves and deletions: patterns, seams, fabrics, colorways and the 3D drape all come back. It also discards anything the user changed by hand in CLO since that point (clo_redo brings it back). The avatar and scene are not part of the history. Restoring resets the list in CLO's own History panel.

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": "clo_undo"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoRestore even though CLO now has a different project open than the one the history was recorded in.
stepsNoHow many changes to step over (default 1).
to_checkpointNoInstead of counting steps, go back to the checkpoint with this label.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full load and does so: it discloses that hand edits in CLO since that point are also discarded, that the avatar/scene fall outside the history, and that restoring resets CLO's own History panel list. These are non-obvious, consequential behaviors an agent could not infer from the schema.

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 destructive effect is front-loaded in the first sentence, scope and side effects follow in a logical order, and every sentence adds distinct information. Nothing is repeated from the name or title.

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 no-annotation mutation tool with no output schema, the description covers what gets restored, what gets destroyed, and what is out of scope. The one gap is the cross-project force scenario, which could silently restore the wrong project's history and is only addressed in the schema description.

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 schema already documents force, steps and to_checkpoint; the description adds the useful hint that multiple changes can be undone ('or several'), which maps to the steps parameter. It does not explain the cross-project force case or checkpoint selection, but that surplus is already in the schema descriptions.

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 opens with a specific verb and scope: undo the last tool call(s) that changed the project by restoring the garment to its prior state. It enumerates the affected domains (patterns, seams, fabrics, colorways, 3D drape) and names the counterpart tool, clo_redo, so the agent can separate the two without opening a schema.

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 states when the tool applies ('everything the tools change, including simulation, moves and deletions'), names the inverse alternative (clo_redo) and its purpose, and carves out an exclusion (the avatar and scene are not part of the history). That is explicit when-to-use, when-not, and alternative guidance.

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