Simpler.Asia

image.variation

[paid: $0.06/image] Generate 1-3 new images from a reference image guided by a prompt (google/nano-banana-2.1, which keeps the reference's product, logo and printed words when the prompt says to): a new scene, background, lighting or layout for the same subject. Pass image_asset_key (an earlier result) or image_url (public https or data:image) plus a prompt describing the change. Each image is stored in this workspace's image library and returned as JSON {images:[{url, asset_key, download_url?, width, height}], price, next} plus a preview; never a provider link. A result with no download_url says why in download_url_unavailable. Refuses: SIMPLER_MEDIA_INPUT_MISSING (pass one image input), SIMPLER_MEDIA_FOREIGN_KEY (use this workspace's asset_key), SIMPLER_MEDIA_URL_REFUSED (use https, data:image or an asset_key), VALIDATION_ERROR on an empty prompt, INSUFFICIENT_CREDITS (add credits), SIMPLER_IMAGE_PROMPT_REFUSED names the label (sexual, minor, real_person or other_unsafe): rewrite the prompt without it, for example no real person's name or likeness; SIMPLER_IMAGE_PROMPT_CHECK_UNAVAILABLE (the safety check is down, nothing charged: retry later); SIMPLER_IMAGE_OUTPUT_FLAGGED (the output failed the content check and was refunded: change the prompt); SIMPLER_IMAGE_OUTPUT_SCAN_UNAVAILABLE (outputs cannot be checked right now, nothing charged: retry later). A partial result lists refunded outputs in output.withheld. To edit a SPECIFIC region use image.inpaint; for whole-image restyle use image.style_transfer. NEXT: pass images[0].asset_key to image.upscale or image.cut_background.

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": "image.variation"
  }
}

Input Schema

Name	Required	Description
`count`	No	Number of variations (1-3, default 1).
`prompt`	Yes	How to vary the image (max 1500 chars).
`image_url`	No	The reference image: a public https URL, a data:image/...;base64 URL, or the url/url_path of an earlier image result (max 20MB; PNG, JPEG, WebP or GIF; SVG is refused). Pass this or the matching *_asset_key, not both.
`request_ref`	No	Optional idempotency key (1-64 chars: letters, digits, . _ : -). Retrying with the same request_ref and the same arguments within 24 hours returns the first result at $0 with replayed: true; the same request_ref with different arguments is refused (SIMPLER_IMAGE_REQUEST_REF_CONFLICT), and so is a retry whose first result was deleted since (SIMPLER_IMAGE_REQUEST_REF_RESULT_DELETED): send a new request_ref to run it again.
`preview_format`	No	Preview block after the JSON, at most 384px on the long edge and never charged: png, jpeg or none. Left out, a PNG result gets a png preview and a JPEG or WebP result a jpeg one. A result with no preview says why in preview_unavailable.
`image_asset_key`	No	The reference image, as the asset_key of an earlier image result for this workspace (edit-projects/<tenant>/... or images/<tenant>/...). A key from another workspace is refused (SIMPLER_MEDIA_FOREIGN_KEY).

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior3/5

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

Annotations expose only readOnlyHint=false, so the description must carry the rest — and it does: price ($0.06/image, zero charge on safety-check failure, refunds on flagged output), workspace-scoped storage, never a provider link, idempotency via request_ref with a 24h replay window. The gaps are secondary: no latency expectation and no statement of concurrency behavior, which keeps this below the top of the scale.

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-loaded with the highest-value facts (price, model, purpose), then inputs, then output shape, then errors and routing. The error enumeration is long but each entry names the code and the recovery action, so it earns its place; sitting in the middle of one paragraph makes it denser than ideal.

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?

With no output schema, the description still gives the full return shape ({images:[{url, asset_key, download_url?, width, height}], price, next} plus a preview), explains download_url_unavailable and withheld outputs, and covers all refusal codes with recovery guidance. An agent has everything needed to call it and handle failures.

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 the baseline is 3; the description earns an extra point by explaining the either/or relationship between image_asset_key and image_url and, importantly, what the prompt parameter controls semantically (it is what preserves product, logo and printed words). request_ref replay/conflict semantics are also restated inline with the error names.

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 1-3 new images from a reference image guided by a prompt"), names the provider model and its preservation behavior, and enumerates the kinds of variation (scene, background, lighting, layout). An agent can distinguish this from image.generate, image.inpaint and image.style_transfer without opening a schema.

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?

Gives explicit routing: "To edit a SPECIFIC region use image.inpaint; for whole-image restyle use image.style_transfer," plus the input requirement (one image input plus a prompt) and a NEXT pointer to image.upscale / image.cut_background. It even states the prompt-conditioned trigger for identity preservation.

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

All Simpler.Asia 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.

Resources

Need Help?