Skip to main content
Glama
Sign In
gimp-mcp

gimp-mcp

by mhbxyz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Create checkpoint

gimp_create_checkpoint

Saves a full checkpoint of the current image state—layers, text, masks, filters, and selection—so you can restore it later, enabling undo/redo.

Instructions

Keep a full copy of the image's current state (layers, text, masks, filters, selection) so it can be restored later: this is how to undo/redo. Copies are hidden from image lists and use memory; at most 20 per image.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "image": "<image>"
    },
    "name": "gimp_create_checkpoint"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYesImage id from gimp_status, e.g. 'image:1@a1b2c3d4'.
labelNo

Output Schema

NameRequiredDescriptionDefault
imageYesImage the checkpoint belongs to (follows restorations).
labelYes
widthYes
heightYes
createdYesUnix time.
checkpointYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Beyond the annotations (which only say non-destructive, non-open-world), the description discloses that copies are hidden from image lists, consume memory, and are capped at 20 per image — real operational constraints an agent can't get from structured fields. It omits what happens at the cap (error vs. eviction), which is the one behavior that would change calling strategy.

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?

Two compact clauses with the core action front-loaded and constraints trailing as subordinate detail. No filler, no restatement of the tool name, and every clause (state captured, undo/redo role, hidden, memory, cap) carries information.

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

Completeness3/5

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

For a snapshot-creating tool the description covers the important dimensions: what is captured, non-destructiveness, and resource limits, and an output schema handles the return value. It is still incomplete on the 'label' parameter and on limit-exceeded behavior, two gaps an agent may hit on real calls.

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

Parameters2/5

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

Schema coverage is only 50% and the description compensates for none of it: the 'image' parameter is never mentioned (the schema itself points to gimp_status for ids), and the entirely undocumented 'label' parameter is passed over completely. An agent gets no guidance on what a label is for or how it surfaces in gimp_list_checkpoints.

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 names a specific action (keep a copy of the image's current state) and enumerates exactly what is captured: layers, text, masks, filters, selection. It also positions the tool functionally ('this is how to undo/redo'), which separates it from gimp_restore_checkpoint, gimp_delete_checkpoint, and the undo-group tools.

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 phrase 'so it can be restored later: this is how to undo/redo' gives a clear situational trigger for calling it. It stops short of explicit exclusions or naming gimp_begin_undo_group/gimp_restore_checkpoint as the alternatives for related workflows, so the agent must infer when a checkpoint beats an undo group.

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