Clipia

generate_image

Generate image(s) from a text prompt, optionally with reference images (editing / image-to-image). Waits briefly for completion and usually returns the finished image inline (URL + small preview). Cost in credits is returned.

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": "generate_image"
  }
}

Input Schema

Name	Required	Description
`seed`	No	Fixes randomness. Only for models that declare seed (see get_model); a model known not to apply it — including the default image model — rejects the call. For distinct variants use num_images, or separate calls with a different idempotency_key each — identical calls within ~20s are de-duplicated to one generation.
`input`	No	Model-specific parameters from get_model input_schema.parameters, keyed by parameter name and merged with the fields above. Some of them (e.g. quality, image_size, image_resolution) change the cost of the call — get_model shows the reference pricing. A misspelled name, or a parameter this model is known not to apply, is rejected before the generation starts; the error lists the parameters the model declares.
`model`	No	Model slug from list_models (slugs may contain '/', e.g. 'google/imagen4' — pass verbatim). Omit to use the default image model.
`prompt`	Yes	What to generate. Russian or English.
`image_urls`	No	Public https URLs of reference images for editing / image-to-image, or several (2–10, model-dependent) to merge subjects, products and styles into one image.
`num_images`	No	How many images to generate in ONE call (model-dependent). Prefer this for multiple variants of a prompt — they come back together as a single tiled result. For variants via separate calls, pass a different idempotency_key each.
`resolution`	No	Output resolution, e.g. '1K', '2K', '4K'. Only for models that declare resolution (see get_model).
`aspect_ratio`	No	Aspect ratio, e.g. '1:1', '16:9', '9:16', '4:3', '3:4'. Model-dependent.
`wait_seconds`	No	How long to wait inline for completion before returning a request_id.
`idempotency_key`	No	Optional stable key (up to 255 characters) to safely retry without creating a duplicate generation. Reuse the same key only when retrying the same request: the same key with a different model or input is rejected with idempotency_key_reuse.
`include_preview`	No	Attach a small inline preview of the finished image to the result.
`negative_prompt`	No	What to avoid. Only for models that declare negative_prompt (see get_model); a model known not to apply it rejects the call.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 5, 2026

changedInput schema / properties / idempotency_key / description

Previous value: -"Optional stable key to safely retry without creating a duplicate generation. Reuse the same key when retrying the same request."New value: +"Optional stable key (up to 255 characters) to safely retry without creating a duplicate generation. Reuse the same key only when retrying the same request: the same key with a different model or input is rejected with idempotency_key_reuse."

addedInput schema / properties / idempotency_key / maxLength
```
Added value: +255
```

First observedNov 2, 2026

TDQS

A4/5.0

Behavior4/5

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

Beyond the annotations, it discloses the inline wait behavior, the typical return shape (URL + small preview), and that credit cost is returned — useful operational context. It stops short of describing what happens on timeout or failure, and the idempotency_key guidance lives only in the schema.

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 tight sentences, front-loaded with the core action and followed by the return/cost behavior. No filler or redundancy.

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 12-parameter tool with a nested input object and no output schema, the description covers the essentials an agent needs: what it produces, that it may return early, and that cost is reported. The async follow-up path is the main omission.

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 schema already carries the parameter burden. The description only adds the notion of optional reference images, which maps to image_urls; it adds no syntax or format detail beyond the schema.

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 a specific verb and resource ('Generate image(s) from a text prompt') plus the optional editing/image-to-image mode, which cleanly separates it from siblings like generate_video, generate_audio, and compose_video.

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?

The description implies usage context (text-to-image vs. reference-image editing) and hints that a request_id may come back when the wait is short, but it never explicitly names get_generation or wait_generation as the follow-up path, nor when to prefer this over generate_video.

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

All Clipia tools Inspect

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.