Skip to main content
Glama

Clip Studio MCP

by ai.clipstudio
OverviewDiscussionsAdmin

generate_image_lab

Start a paid Image Lab generation (ChatGPT Image 2.5, Nano Banana, Nano Banana 2, Nano Banana 2.1, Nano Banana Pro, FLUX 3 Image, FLUX.2 Pro, Ideogram V4.5, MAI Image 2.5, MAI Image 2.5 Pro, Seedream 5 Lite, Seedream 5 Flash, Muse Image, Grok Imagine Image 2.0, Qwen Image 3, Kling Omni 3, or Recraft V4.1 Flash). Uses this month’s generation allowance. Poll get_image_lab_generation until it finishes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNotext_to_image or image_to_image. Must match the quote when quoteId is set. Same as inputMode.
promptNoWhat to draw. Omit when quoteId is set.
quoteIdNoQuote id from quote_image_lab. Optional; generate quotes first when omitted if modelSlug and prompt are set.
inputModeNoSame as mode: text_to_image or image_to_image.
modelSlugNoImage Lab model slug from list_image_lab_models. Required unless quoteId is set.
aspectRatioNoStill aspect from list_image_lab_models for that slug. Omit when quoteId is set.
sourceAssetIdsNoSame source still asset ids used on the quote. Omit when quoteId is set.
sourceImageAssetIdNoSource still generation-asset id for image_to_image. Omit when quoteId is set.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNoJob status such as pending, queued, in_progress, completed, or failed.
videoIdNoLibrary clip id for this job, when one exists.
idempotentNoTrue when this call reused an in-flight or finished job with the same idempotency key.
generationIdYesGeneration id. Poll the matching get_* tool until status is completed or failed.
creditsChargedNoUsage already consumed from this month’s generation allowance (internal units).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedInput schema / properties / aspectRatio / description
      Previous value: -"Still aspect from the catalog. Must match the quote when quoteId is set."New value: +"Still aspect from list_image_lab_models for that slug. Omit when quoteId is set."
    • addedInput schema / properties / inputMode
      Added value: +{
+  "description": "Same as mode: text_to_image or image_to_image.",
+  "type": "string"
+}
    • changedInput schema / properties / mode / description
      Previous value: -"text_to_image or image_to_image. Must match the quote when quoteId is set."New value: +"text_to_image or image_to_image. Must match the quote when quoteId is set. Same as inputMode."
    • changedInput schema / properties / prompt / description
      Previous value: -"What to draw. Must match the quoted setup when quoteId is set."New value: +"What to draw. Omit when quoteId is set."
    • changedInput schema / properties / sourceAssetIds / description
      Previous value: -"Same source still asset ids used on the quote."New value: +"Same source still asset ids used on the quote. Omit when quoteId is set."
    • addedInput schema / properties / sourceImageAssetId
      Added value: +{
+  "description": "Source still generation-asset id for image_to_image. Omit when quoteId is set.",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "prompt"
-]
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly=false, destructive=false, openWorld=false; the description adds the behavior the annotations cannot: the call is billed against a monthly generation allowance and is asynchronous (poll a sibling until it finishes). That is meaningful non-schema context, though quota-exhaustion and failure behavior are unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and the polling instruction are front-loaded and useful, but the first sentence is dominated by an 18-item model name dump that largely duplicates list_image_lab_models rather than earning its place inline. Two sentences are appropriately short overall, yet a third of the token budget is a catalog listing.

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, return values need not be explained, and the description covers the two things structured fields omit: cost/allowance semantics and the async poll flow. It is close to complete for this tool, missing only prerequisite ordering (quote first vs supply modelSlug+prompt).

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 eight parameters (mode vs inputMode aliasing, quoteId-vs-modelSlug/prompt exclusivity, aspectRatio derivation) are already fully documented in the schema. The description adds only the model-slug vocabulary, not any parameter syntax or constraints beyond it.

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?

Starts with a specific verb+resource ('Start a paid Image Lab generation'), scopes it as the paid generation entry point, and names the sibling used to follow up (get_image_lab_generation). An agent can distinguish it from quote_image_lab and list_image_lab_models from the description 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?

It tells the agent the operation is paid, consumes this month's allowance, and requires polling get_image_lab_generation until finished, which is genuine workflow guidance. However it never states when to use this versus quote_image_lab first, nor what happens if the allowance is exhausted — prerequisites live only in the schema's quoteId description.

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

All Clip Studio MCP 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