Galatic.ai

Prompt suggestions

get_prompt_suggestions

Read-onlyIdempotent

Get example prompts from the Galatic.AI prompt library. With modelId, returns up to 6 examples for that model (count defaults to 3; category, contentType and style are ignored). Without modelId, category is required (a template category id; the call fails without it) and returns up to 8 suggestions (count defaults to 4), optionally narrowed by contentType ("image", "video" or "audio") and style. Returns { prompts, source }. Use when the user wants ideas for what to make; use improve_prompt instead to rewrite a prompt they already have. Read-only, spends no credits.

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": {
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "get_prompt_suggestions"
  }
}

Input Schema

Name	Required	Description
`count`	No	How many prompts. Capped at 8 (6 with modelId).
`style`	No	Style preset. Ignored with modelId.
`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."
`modelId`	No	Model id, e.g. "google/veo-3-1". When set, only count is used.
`category`	No	Template category id. Required when modelId is not set.
`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.
`contentType`	No	"image", "video" or "audio". Ignored with modelId.
`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.

Changed5 schema fields changedOct 26, 2026

addedInput schema / properties / category / description

Added value: +"Template category id. Required when modelId is not set."

addedInput schema / properties / contentType / description

Added value: +"\"image\", \"video\" or \"audio\". Ignored with modelId."

addedInput schema / properties / count / description

Added value: +"How many prompts. Capped at 8 (6 with modelId)."

addedInput schema / properties / modelId / description

Added value: +"Model id, e.g. \"google/veo-3-1\". When set, only count is used."

addedInput schema / properties / style / description

Added value: +"Style preset. Ignored with modelId."

First observedOct 24, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Goes well beyond the annotations: it discloses the two disjoint calling modes, the differing result caps (6 vs 8), the differing count defaults (3 vs 4), which parameters get silently ignored, the hard failure when category is missing without modelId, and that the call spends no credits. The only thing it doesn't cover is what 'source' in the response means, but the values of that field are self-evident.

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 resource, then the mode branching, then the routing rule — a logical order with no filler. It is denser than typical but nearly every clause carries a distinct constraint; the prose is slightly packed into one long block.

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?

An 8-parameter tool with conditional requirements and no output schema is fully covered: branching preconditions, defaults, caps, ignored params, the failure mode, the return shape ({ prompts, source }), and cost profile are all present. Nothing an agent needs to call it correctly is missing.

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, but the description adds information the schema lacks: default values (3 with modelId, 4 without) and the mutual-exclusion rule that category/contentType/style are ignored when modelId is set. It does not explain count's interaction with the cap beyond repeating 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 ('Get example prompts from the Galatic.AI prompt library') and immediately names the sibling it is not ('use improve_prompt instead to rewrite a prompt they already have'), so the agent can route without opening either 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 when-to-use ('user wants ideas for what to make') coupled with an explicit alternative and the condition that selects it ('use improve_prompt to rewrite a prompt they already have'). The two calling modes (with/without modelId) are also spelled out with their own preconditions.

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.