Skip to main content
Glama

Claude Imagine

by com.claudeimagine
OverviewDiscussionsAdmin

Generate Image

generate_image
Destructive

Generate an AI image from a text prompt using Claude Imagine credits. Returns the image inline plus its full-resolution URL. To change an existing image, use edit_image. For a YouTube thumbnail, book cover, album or podcast cover, poster, blog cover or product photo, call list_styles first and pass one of its ids as style.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoModel to use. nano-banana-2 (default, best quality/price), gpt-image-2.5, seedream-4.5, flux-2-pro, z-image (fastest & cheapest)
styleNoA named look from list_styles, e.g. thumbnail-bold. The prompt then describes only the subject: what is in the picture, and any words that must appear in it in double quotes. The style sets the framing and the aspect ratio; aspect_ratio still overrides it.
promptYesImage description
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. When omitted, the selected model's own default is used.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / style
      Added value: +{
+  "description": "A named look from list_styles, e.g. thumbnail-bold. The prompt then describes only the subject: what is in the picture, and any words that must appear in it in double quotes. The style sets the framing and the aspect ratio; aspect_ratio still overrides it.",
+  "enum": [
+    "thumbnail-bold",
+    "thumbnail-clean",
+    "thumbnail-cinematic",
+    "thumbnail-tech",
+    "book-literary",
+    "book-thriller",
+    "book-romance",
+    "book-fantasy",
+    "cover-minimal",
+    "cover-neon",
+    "cover-vintage",
+    "cover-portrait",
+    "poster-movie",
+    "poster-event",
+    "poster-retro",
+    "poster-photo",
+    "blog-editorial",
+    "blog-flat",
+    "blog-photo",
+    "blog-isometric",
+    "product-studio",
+    "product-lifestyle",
+    "product-marble",
+    "product-nature"
+  ],
+  "type": "string"
+}
  2. 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."
  3. 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"
+}
  4. Changed2 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"Model to use. nano-banana-2 (default, best quality/price), gpt-image-2, seedream-4.5, flux-2-pro, z-image (fastest & cheapest)"New value: +"Model to use. nano-banana-2 (default, best quality/price), gpt-image-2.5, seedream-4.5, flux-2-pro, z-image (fastest & cheapest)"
    • changedInput schema / properties / model / enum
      Previous value: -[
-  "nano-banana-2",
-  "gpt-image-2",
-  "seedream-4.5",
-  "flux-2-pro",
-  "z-image"
-]New value: +[
+  "nano-banana-2",
+  "gpt-image-2.5",
+  "seedream-4.5",
+  "flux-2-pro",
+  "z-image",
+  "gpt-image-2"
+]
  5. 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"
+}
  6. Changed1 schema field changed
    • changedInput schema / properties / aspect_ratio / description
      Previous value: -"Aspect ratio, default 1:1"New value: +"Aspect ratio. When omitted, the selected model's own default is used."
  7. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Description notes that the tool 'Returns the image inline plus its full-resolution URL', which is useful beyond annotations. It hints at credit consumption ('using... credits'), but annotations already mark destructiveHint=true. No contradiction; the description adds context that generation consumes credits and returns a URL, which is valuable given the annotations don't cover return format.

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?

Description is compact, with front-loaded purpose and return info. The additional usage guidance is essential and concise. Slightly long due to the resolution parameter explanation, but that's in the schema, not the main description, so overall the main description is efficient.

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

Completeness5/5

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

Given the tool's complexity (6 params, 4 enums, no output schema), the description covers purpose, usage, return format, and routing to siblings. Missing output schema is compensated by describing the return. All critical aspects for correct invocation are addressed.

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. Description adds significant value: explains that style sets framing and aspect ratio (and prompt should only describe subject), that resolution is for size signals only with detailed guidance, and that max_credits is a budget cap. This goes beyond 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?

States the verb ('Generate'), resource ('AI image'), input ('text prompt'), and an explicit tie to 'Claude Imagine credits', distinguishing it from siblings like edit_image and generate_video. The first sentence is specific and unambiguous.

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?

Explicitly tells when to use the tool (new image from prompt) and when not (to change an existing image, use edit_image). It also instructs to call list_styles first for specific use cases (e.g., YouTube thumbnail, book cover) and pass its id as style. This is clear, actionable routing.

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