Skip to main content
Glama

Create an image

create_image
Destructive

Starts making one or more images and spends their credits (refunded if it fails). Poll get_generation with the id.

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": "create_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoQuality tier: quick (cheapest), great (best value, default), cinema (most realistic). Or give `model` instead.
imageNoOptional start image: base64 JPEG, PNG or WebP (a data: URL works), under 10 MB.
modelNoA model id from list_models, instead of a tier.
promptYesWhat to make, in plain words. @handles use the person's saved characters.
image_idNoOptional start image already sent to POST /v1/uploads.
num_imagesNoImages to make, up to the model's max_images.
resolutionNoe.g. "720p" or "1080p" for videos, "2K" for images. Defaults to the tier's.
max_creditsNoRefuse instead of spending more than this many credits.
aspect_ratioNoAspect ratio, e.g. "16:9", "9:16" (vertical, for Reels and TikTok) or "1:1".
photo_consentNoRequired with an image: true only if the person confirmed they have the right to use it and the people in it agree.
idempotency_keyNoRetrying with the same key never creates twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description adds the key context those annotations cannot: credits are spent up front and refunded on failure. That directly explains the destructive cost profile. It stops short of describing credit reservation timing or how failures are surfaced beyond the refund note.

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?

Two short sentences with zero filler; the cost/refund caveat and the follow-up polling step are both front-loaded and immediately actionable.

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 an 11-parameter, non-idempotent, credit-spending tool with no output schema, the definition covers the cost side effect and the handoff to get_generation, which is the essential flow. It omits how to discover models/tiers or check balance first, but the full schema coverage and annotations carry most of the remaining burden.

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 all 11 parameters (tier, image, model, max_credits, photo_consent, idempotency_key, etc.) are already documented in structured data. The description adds only the implication that an id is returned for polling, which is marginal value over the schema.

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?

The description uses a specific verb and resource ("Starts making one or more images") and states the immediate consequence (spending credits). The word "images" implicitly separates it from create_video, create_film and create_ad, but no sibling is named as an explicit contrast.

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 gives clear next-step guidance ("Poll get_generation with the id") but no when-to-use guidance relative to alternatives such as estimate_cost, get_balance, or create_video. Usage context is implied by the resource type rather than stated.

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