Skip to main content
Glama

Claude Imagine

by com.claudeimagine
OverviewDiscussionsAdmin

Edit Image

edit_image
Destructive

Edit an existing image with a text instruction, using Claude Imagine credits. Pass the full-resolution URL of the image to change; the result is a new image, the original is untouched. Say in the prompt what must stay the same, not only what changes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoEditing model. nano-banana-2 (default) or gpt-image-2.5. The other image models cannot edit through MCP yet.
promptYesWhat to change, and what to keep. Example: "replace the sky with a sunset, keep the people and the framing unchanged"
image_urlsYesPublic URL of the image to edit, normally the full-resolution URL returned by an earlier generation. One image in this version.
resolutionNoOutput size: 1k, 2k or 4k. Leave it out unless the user gave a clear size signal: a pixel size or tier (4K, 2K, high resolution) or a physical output (print, poster, wallpaper, billboard). Words like premium, professional or high quality describe the look, not the size, and are not a reason to pass this. Omitted uses the model's default, its cheapest size; 2k and 4k cost roughly two to three times more credits and take longer. When the user asks for 'sharper' or 'bigger' without a size, quote_generation the options and ask which one.
max_creditsNoBudget cap in credits, when the person stated one. If the exact cost of this call is above it, nothing is started and the reply lists what fits.
aspect_ratioNoAspect ratio for the result. When omitted, the framing of the source image is kept.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / resolution / description
      Previous value: -"Output size: 1k, 2k or 4k. Omitted means the model's default (its cheapest size). Larger sizes cost more credits; quote_generation shows the exact price."New value: +"Output size: 1k, 2k or 4k. Leave it out unless the user gave a clear size signal: a pixel size or tier (4K, 2K, high resolution) or a physical output (print, poster, wallpaper, billboard). Words like premium, professional or high quality describe the look, not the size, and are not a reason to pass this. Omitted uses the model's default, its cheapest size; 2k and 4k cost roughly two to three times more credits and take longer. When the user asks for 'sharper' or 'bigger' without a size, quote_generation the options and ask which one."
  2. Changed1 schema field changed
    • addedInput schema / properties / resolution
      Added value: +{
+  "description": "Output size: 1k, 2k or 4k. Omitted means the model's default (its cheapest size). Larger sizes cost more credits; quote_generation shows the exact price.",
+  "enum": [
+    "1k",
+    "2k",
+    "4k"
+  ],
+  "type": "string"
+}
  3. Changed2 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"Editing model. nano-banana-2 (default) or gpt-image-2. The other image models cannot edit through MCP yet."New value: +"Editing model. nano-banana-2 (default) or gpt-image-2.5. The other image models cannot edit through MCP yet."
    • changedInput schema / properties / model / enum
      Previous value: -[
-  "nano-banana-2",
-  "gpt-image-2"
-]New value: +[
+  "nano-banana-2",
+  "gpt-image-2.5",
+  "gpt-image-2"
+]
  4. Changed1 schema field changed
    • addedInput schema / properties / max_credits
      Added value: +{
+  "description": "Budget cap in credits, when the person stated one. If the exact cost of this call is above it, nothing is started and the reply lists what fits.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
  5. Added

TDQS

A3.6/5.0
Behavior1/5

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

Annotation Contradiction: destructiveHint=true implies destructive behavior, but the description explicitly says 'the original is untouched' and 'the result is a new image.' This direct contradiction makes the behavioral profile unreliable, so a score of 1 is required.

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?

Three sentences, no filler, and the core action is front-loaded. The guidance about preserving content earns its place and does not bloat the description.

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?

Covers the non-obvious operational facts: credit usage, non-destructive output, and prompt phrasing advice. It does not explicitly discuss cost quoting or when to prefer a generation tool, but the rich schema and sibling context make those gaps minor.

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?

Schema description coverage is 100%, so the baseline is 3. The description adds minor value by advising use of the full-resolution URL and emphasizing that the prompt should preserve unchanged content, but the schema already documents all parameters thoroughly.

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?

States a specific verb ('Edit'), resource ('existing image'), and method ('text instruction'). The contrast between 'result is a new image' and 'original is untouched' clearly distinguishes it from generation-focused siblings like generate_image.

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?

Provides clear context for when to use the tool: editing an existing image, not creating one. It also gives a practical prompt-construction rule ('say what must stay the same'), but it does not explicitly name sibling alternatives or state when not to use this tool.

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

All Claude Imagine toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources