Galatic.ai

Ad creative

create_ad_creative

Generate an ad image with a text overlay. baseImageUrl and overlayConfig.headshotUrl must be your own uploads, or the request gets 400 before any credits are reserved. Spends Galatic.AI credits. Returns a job id; poll get_job_status with kind "ad_creative".

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": "create_ad_creative"
  }
}

Input Schema

Name	Required	Description
`model`	No	Image model id from list_models. Defaults to "flux-pro".
`prompt`	Yes	What the ad image shows.
`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, passed through to the image model.
`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.
`baseImageUrl`	No	Your own uploaded image, used as the base. With skipGeneration it is the image the overlay goes onto.
`overlayConfig`	No	Text overlay: copy fields, layout, agentName, phoneNumber, and headshotUrl (your own uploaded image).
`skipGeneration`	No	True to skip making a new image and compose the overlay onto baseImageUrl.
`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 / baseImageUrl / description

Added value: +"Your own uploaded image, used as the base. With skipGeneration it is the image the overlay goes onto."

addedInput schema / properties / model / description

Added value: +"Image model id from list_models. Defaults to \"flux-pro\"."

addedInput schema / properties / overlayConfig / description

Added value: +"Text overlay: copy fields, layout, agentName, phoneNumber, and headshotUrl (your own uploaded image)."

addedInput schema / properties / prompt / description
```
Added value: +"What the ad image shows."
```

addedInput schema / properties / settings / description

Added value: +"Model-specific options, passed through to the image model."

addedInput schema / properties / skipGeneration / description

Added value: +"True to skip making a new image and compose the overlay onto baseImageUrl."

First observedOct 24, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations declare the mutation/idempotency profile but say nothing about cost, failure ordering, or async flow. The description supplies all three: it spends Galatic.AI credits, validation failure happens before credits are reserved, and the tool is asynchronous via a job id. That is genuine value beyond the structured fields.

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?

Three tight sentences: purpose first, then the constraint that prevents a failed call, then the return/poll contract. No filler and no repetition of what the schema already spells out.

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 9-parameter tool with nested objects and no output schema, the description covers the two things an agent most needs and cannot infer: that it costs credits and that it returns a job id requiring polling. Remaining gaps (skipGeneration composition path, settings passthrough) are adequately handled by the 100%-covered schema.

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, and the description exceeds it by adding an ownership/validation constraint on two specific parameters (baseImageUrl, overlayConfig.headshotUrl) that the schema does not state. It stops short of explaining skipGeneration or settings, which remain schema-only.

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 an ad image with a text overlay") and immediately scopes it to a particular artifact type, which separates it from generic siblings like generate_image and edit_image. The closing sentence adds the return contract (job id, kind "ad_creative"), so an agent knows both what it makes and what it hands back.

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 a concrete precondition (baseImageUrl and overlayConfig.headshotUrl must be own uploads, or a 400 occurs before credits are reserved) and explicit post-call routing (poll get_job_status with kind "ad_creative"). It does not say when to prefer this over generate_image/edit_image for non-ad work, so the sibling-selection guidance is incomplete.

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.