Galatic.ai

Generate image

generate_image

Generate images from a prompt. model is required by the server (400 without it): a model id from list_models, such as "flux-pro"; video models are refused. count makes 1-4 images and is charged per image. imageUrls is used only by image-to-image models, which require it; text-to-image models ignore it. Most models run in the background and return the id as job_id; a few answer at once with { images } already saved to the library. With count above 1, the status poll reports complete after the first image; find the rest with list_gallery. Spends Galatic.AI credits. Returns a job id; poll get_job_status with kind "image".

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>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "generate_image"
  }
}

Input Schema

Name	Required	Description
`count`	No	1-4 images, each charged.
`model`	No	Required by the server: an image model id from list_models.
`style`	No	Optional style preset applied to the prompt.
`prompt`	Yes	What to draw.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`settings`	No	Model-specific options, e.g. aspect ratio.
`imageUrls`	No	Source images, for image-to-image models only.
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 27, 2026
- addedInput schema / properties / count / description
```
Added value: +"1-4 images, each charged."
```
- addedInput schema / properties / imageUrls / description
```
Added value: +"Source images, for image-to-image models only."
```
- addedInput schema / properties / model / description
```
Added value: +"Required by the server: an image model id from list_models."
```
- addedInput schema / properties / prompt / description
```
Added value: +"What to draw."
```
- addedInput schema / properties / settings / description
```
Added value: +"Model-specific options, e.g. aspect ratio."
```
- addedInput schema / properties / style / description
```
Added value: +"Optional style preset applied to the prompt."
```
First observedOct 24, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Adds substantial context beyond the annotations (readOnlyHint=false, idempotentHint=false): the call spends Galatic.AI credits and is charged per image, model is mandatory server-side (400 without it), and most models are asynchronous while a few return { images } synchronously. It even discloses the status-poll quirk where count > 1 reports complete after the first image. This is exactly the kind of non-obvious operational behavior annotations cannot convey.

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 core action, and nearly every sentence carries a distinct operational fact. It runs dense with multiple clauses per sentence, which slightly hurts scanability for a seven-sentence description, but there is no filler.

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 takes on the burden of describing returns (job_id vs. { images } already saved to the library) and the follow-up polling path. For a 9-parameter tool with nested settings and no output schema, nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3), but the description goes further by flagging that model is effectively required despite not appearing in the required array, that count is billed per image, and that imageUrls is conditionally mandatory. That resolves real ambiguities the schema leaves open.

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 images from a prompt) and actively separates itself from siblings: video models are refused, and imageUrls applies only to image-to-image models rather than edit_image-style flows. An agent can distinguish this from generate_video and edit_image without opening any 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?

Explicit routing instructions: get the model id from list_models, poll get_job_status with kind "image", and use list_gallery to find extra images when count > 1. It also names the condition that selects imageUrls (image-to-image models only).

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

All Galatic.ai 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.