Skip to main content
Glama

Claude Imagine

by com.claudeimagine

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. 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.
aspect_ratioNoAspect ratio for the result. When omitted, the framing of the source image is kept.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A3.8/5.0
Behavior1/5

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

The description explicitly claims 'the original is untouched' and 'the result is a new image', while annotations declare destructiveHint=true. This is a direct contradiction about the tool's behavioral impact. The description does add useful context about Claude Imagine credits, but the contradiction is a serious transparency failure.

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, each earning its place: the first defines the operation and cost, the second specifies input and output behavior, and the third gives a critical prompt tip. The most important information is front-loaded and there is no filler.

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 four-parameter tool with full schema documentation, the description covers the core use case, key parameter behavior, and output semantics ('result is a new image'). The main gap is the unresolved contradiction with the destructiveHint annotation, which prevents fully trusting the description as complete.

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 baseline is 3. The description adds value beyond the schema by specifying that image_urls should be the 'full-resolution URL' from an earlier generation and by advising prompt authors to state what must stay the same. This gives practical parameter-level guidance that the schema alone does not fully convey.

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 action ('Edit an existing image with a text instruction'), names the resource ('existing image'), and clarifies the output ('result is a new image, the original is untouched'). This clearly distinguishes edit_image from siblings like generate_image and generate_video.

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 makes clear this is for editing existing images, implying generate_image is for new creations, and gives practical usage guidance: pass the full-resolution URL and state what must stay the same. It does not explicitly name sibling alternatives or state when not to use it, but the context is sufficiently clear.

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
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool maps cleanly to a distinct action: generate new media, edit media, retrieve by ID, list history, view models, check credits, and quote a potential cost. Even check_generation and list_generations are clearly separated by lookup-by-id versus listing. No two tools appear to do the same thing.

Naming Consistency5/5

Every tool follows the same verb_noun snake_case pattern, such as generate_image, list_models, and quote_generation. The verbs are descriptive and consistently chosen for each operation. This makes the tool surface highly predictable for an agent.

Tool Count5/5

Eight tools is well-scoped for a media generation server covering image generation, video generation, editing, history retrieval, model discovery, and credit management. Each tool serves a clear purpose without redundancy or feature bloat.

Completeness5/5

The tool set covers the full generation lifecycle: creating images, creating videos, editing images, checking generation status, listing past results, inspecting models and costs, quoting prices, and checking credits. There are no obvious dead ends or missing core operations for the stated domain.

Resources