gimp-mcp

Overview Schema Source Related Servers Discussions Admin

Inspect image

gimp_inspect_image

Read-only

Inspect a GIMP image to retrieve its size, mode, precision, resolution, unsaved changes, associated files, and complete ordered layer tree without relying on the active selection.

Instructions

Describe one image: size, mode, precision, resolution, unsaved changes, associated files and the full ordered layer tree (groups, children, masks, offsets, opacity, blend mode, locks). Does not depend on GIMP's active selection.

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_inspect_image"
  }
}

Input Schema

Name	Required	Description	Default
`image`	Yes	Image id from gimp_status, e.g. 'image:1@a1b2c3d4'.

Output Schema

Name	Required	Description
`id`	Yes
`file`	Yes
`name`	Yes	GIMP's display name (may be localized).
`unit`	No	Display/print unit abbreviation, e.g. 'in', 'mm'.
`dirty`	Yes
`paths`	No	Paths (vectors), top first.
`width`	Yes
`height`	Yes
`layers`	Yes	Layer tree, top-most layer first.
`channels`	No	Saved selections and masks.
`xcf_file`	Yes	XCF file the image was loaded from or saved to.
`base_type`	Yes	'rgb', 'gray' or 'indexed'.
`precision`	Yes
`resolution`	Yes
`exported_file`	Yes
`imported_file`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.6.0Nov 10, 2026

addedOutput schema / $defs / ChannelSummary

Added value: +{
+  "properties": {
+    "color": {
+      "title": "Color",
+      "type": "string"
+    },
+    "id": {
+      "title": "Id",
+      "type": "string"
+    },
+    "name": {
+      "title": "Name",
+      "type": "string"
+    },
+    "opacity": {
+      "title": "Opacity",
+      "type": "number"
+    },
+    "show_masked": {
+      "title": "Show Masked",
+      "type": "boolean"
+    },
+    "visible": {
+      "title": "Visible",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "id",
+    "name",
+    "visible",
+    "opacity",
+    "color",
+    "show_masked"
+  ],
+  "title": "ChannelSummary",
+  "type": "object"
+}

changedOutput schema / $defs / LayerNode / properties / kind / enum

Previous value: -[
-  "layer",
-  "group",
-  "text"
-]New value: +[
+  "layer",
+  "group",
+  "text",
+  "vector",
+  "link"
+]

addedOutput schema / $defs / PathSummary

Added value: +{
+  "properties": {
+    "id": {
+      "title": "Id",
+      "type": "string"
+    },
+    "name": {
+      "title": "Name",
+      "type": "string"
+    },
+    "strokes": {
+      "title": "Strokes",
+      "type": "integer"
+    },
+    "visible": {
+      "title": "Visible",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "id",
+    "name",
+    "visible",
+    "strokes"
+  ],
+  "title": "PathSummary",
+  "type": "object"
+}

addedOutput schema / properties / channels

Added value: +{
+  "description": "Saved selections and masks.",
+  "items": {
+    "$ref": "#/$defs/ChannelSummary"
+  },
+  "title": "Channels",
+  "type": "array"
+}

addedOutput schema / properties / paths

Added value: +{
+  "description": "Paths (vectors), top first.",
+  "items": {
+    "$ref": "#/$defs/PathSummary"
+  },
+  "title": "Paths",
+  "type": "array"
+}

addedOutput schema / properties / unit

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Display/print unit abbreviation, e.g. 'in', 'mm'.",
+  "title": "Unit"
+}

First observedv0.1.0Nov 7, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: it discloses exactly what data is returned (including unsaved-changes state and associated files) and the notable behavioral trait that it ignores GIMP's active selection.

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?

Front-loaded with the core action, then one dense parenthetical listing returned fields, then a short constraint clause. Every element earns its place; the parenthetical is long but replaces a vague "returns details".

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?

With an output schema present the return values need not be spelled out, yet the description still summarizes them, and read-only semantics are covered by annotations. The only gap is the absence of explicit routing against the two sibling inspect tools.

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

Parameters3/5

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

Single parameter with 100% schema description coverage that already explains the id format ('image:1@a1b2c3d4') and its origin in gimp_status. The description adds nothing about the parameter, so the baseline 3 for high-coverage schemas applies.

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?

"Describe one image" gives a specific verb and resource, and the enumeration (size, mode, precision, resolution, layer tree, masks, offsets, opacity, blend mode, locks) makes the scope concrete. It never names a sibling like gimp_inspect_item or gimp_inspect_text, so the agent must infer the split from the resource word "image" alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: "Does not depend on GIMP's active selection" signals this is safe to call when no image/selection context is established, which is a real hint about when to prefer it. There is no explicit when-to-use vs gimp_inspect_item/gimp_inspect_text guidance and no stated prerequisites.

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

Deploy Server