Skip to main content
Glama

Studio: generate image

studio_generate_image
Destructive

Generate a single image via the Studio model catalog (call list_studio_models for keys/pricing). SYNC — the asset URL comes back in the result. SPENDS CREDITS (per-model, see creditCost). Reference images can be passed as URLs (use import_asset_from_url / create_upload first if needed). negativePrompt applies only to models whose capabilities include supportsNegativePrompt (e.g. NOT BytePlus/Seedream); on other models it is ignored, not an error.

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": {
      "prompt": "<prompt>"
    },
    "name": "studio_generate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYes
qualityNoOnly on models with supportsImageQuality; the allowed tiers are capabilities.imageQualities (xhigh/max: GPT Image 2.6 only). Credits vary by tier, see pricing.imageCreditsByQuality.
modelKeyNo
aspectRatioNo
outputFormatNoOnly on models with capabilities.imageOutputFormats; default png
referenceModeNo
thinkingLevelNoReasoning effort, only on models with imageThinkingLevels (P-Image Ideogram; GPT Image 2.6 takes low/medium/high)
negativePromptNoIgnored on models without supportsNegativePrompt (see list_studio_models).
imageResolutionNoOutput size, only on models with capabilities.imageResolutions. Credits vary by size, see pricing.imageCreditsByResolution.
referenceImagesNoReference image URLs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / imageResolution
      Added value: +{
      +  "description": "Output size, only on models with capabilities.imageResolutions. Credits vary by size, see pricing.imageCreditsByResolution.",
      +  "enum": [
      +    "1K",
      +    "2K",
      +    "4K"
      +  ],
      +  "type": "string"
      +}
  2. Changed3 schema fields changed
    • addedInput schema / properties / outputFormat
      Added value: +{
      +  "description": "Only on models with capabilities.imageOutputFormats; default png",
      +  "enum": [
      +    "png",
      +    "jpeg",
      +    "webp"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / quality
      Added value: +{
      +  "description": "Only on models with supportsImageQuality; the allowed tiers are capabilities.imageQualities (xhigh/max: GPT Image 2.6 only). Credits vary by tier, see pricing.imageCreditsByQuality.",
      +  "enum": [
      +    "low",
      +    "medium",
      +    "high",
      +    "xhigh",
      +    "max",
      +    "auto"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / thinkingLevel / description
      Previous value: -"P-Image Ideogram reasoning effort; omit for other image models"New value: +"Reasoning effort, only on models with imageThinkingLevels (P-Image Ideogram; GPT Image 2.6 takes low/medium/high)"
  3. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already flag a non-idempotent, open-world, mutating operation, and the description adds material context beyond them: it explicitly warns that the call SPENDS CREDITS (per-model), that it is SYNC so the asset URL returns directly, and that unsupported parameters are ignored rather than erroring. That cost and failure-mode disclosure is exactly what an agent needs before invoking a paid write operation.

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-loads the action, then the sync behavior, then the credit warning, so the most decision-relevant facts come first. The remaining sentences are dense with parentheticals and model-name caveats but each conveys distinct operational information.

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 10-parameter, capability-gated generation tool with no output schema, the description covers the critical unknowns: cost, synchronous return of the asset URL, reference-image prerequisites, and per-model parameter gating. The main gap is that aspectRatio and referenceMode semantics are left entirely to the enums.

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?

With 60% schema coverage, the description adds real meaning on top of the schema: it explains that modelKey is looked up via list_studio_models, that referenceImages are URL-based and may require prior import, and that negativePrompt's gating is a capability check rather than an error. It adds nothing for aspectRatio or referenceMode, whose enum values carry unexplained semantics.

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?

States a specific verb and resource ('Generate a single image via the Studio model catalog'), which is concrete enough to distinguish it from the influencer/seedance image siblings by its model-catalog framing. It does not, however, explicitly contrast itself with generate_influencer_studio_image or seedance_generate_image, so the differentiation is inferred rather than stated.

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?

Gives actionable usage context: consult list_studio_models for keys/pricing, use import_asset_from_url or create_upload before passing reference images, and expect negativePrompt to be silently ignored on unsupported models. It stops short of saying when to choose this tool over the other image-generation siblings.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources