Galatic.ai

Character reference

create_character_reference

Generate one reference-image candidate for a character in a series and return { name, outfit, referenceUri, previewUrl } when it is ready (it waits; no job to poll). Generation takes close to 30 s; if the request times out it checks for the finished image itself. If it is still not done it names a requestId: check it with get_job_status, kind "character_reference" (free), rather than starting a new request. The candidate is not saved on the character: to keep it, set that character's referenceImageUri with save_flow. name must match a character in the series that has a visual description. Spends Galatic.AI credits for one image (402 when the budget is short). seriesId is the flowId of the Flow Studio flow that holds the series (from list_flows).

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": {
      "seriesId": "<seriesId>",
      "name": "<name>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "create_character_reference"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	The character's exact name in the series.
`outfit`	No	Default everyday. spacesuit needs a spacesuitDesign on the series.
`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."
`seriesId`	Yes
`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.
`requestId`	No	Optional. Made for you when omitted. Reuse the SAME requestId to retry: a finished image comes back without a second charge.
`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.

Changed3 schema fields changedNov 3, 2026

addedInput schema / properties / outfit

Added value: +{
+  "description": "Default everyday. spacesuit needs a spacesuitDesign on the series.",
+  "enum": [
+    "everyday",
+    "spacesuit"
+  ],
+  "type": "string"
+}

changedInput schema / properties / requestId / description

Previous value: -"Optional client id for this request."New value: +"Optional. Made for you when omitted. Reuse the SAME requestId to retry: a finished image comes back without a second charge."

addedInput schema / properties / requestId / pattern
```
Added value: +"^[a-z0-9-]{8,64}$"
```

Changed2 schema fields changedOct 27, 2026
- addedInput schema / properties / name / description
```
Added value: +"The character's exact name in the series."
```
- addedInput schema / properties / requestId / description
```
Added value: +"Optional client id for this request."
```
First observedOct 24, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses that the call blocks ~30 s, self-recovers on timeout, spends credits with a 402 on short budget, and produces an unsaved candidate. The only meaningful gap is that reusing requestId to get a finished image without a second charge sits in tension with idempotentHint=false, which is not reconciled. No contradiction, but this ambiguity keeps it below 5.

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?

Dense and front-loaded: the core action and return shape come first, then timeout handling, then persistence, then constraints. The clauses are long and run together with semicolons, which slightly hurts scanability, but nothing is 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 compensates by naming the return fields, the blocking timing, failure modes, cost, and non-persistence. For a 7-parameter credit-spending generation tool, an agent has everything needed to call it correctly and to handle the aftermath.

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 86%, so the baseline is 3; the description still adds meaning by explaining that seriesId is the flowId of the Flow Studio flow from list_flows, and that name must match a character in the series that has a visual description. The outfit and requestId semantics are left to the schema, which already documents them well.

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?

The opening sentence states a specific verb and resource — generate one reference-image candidate for a character in a series — and even names the returned fields { name, outfit, referenceUri, previewUrl }. It is clearly distinguishable from sibling image-related tools like create_ad_creative because it is scoped to a character within a series flow.

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 is given for every branch: on timeout, check with get_job_status (kind "character_reference") instead of starting a new request; to persist the result, set referenceImageUri via save_flow; seriesId comes from list_flows. The agent is told both what to do and what not to do at each decision point.

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.