Skip to main content
Glama

novai_generate_image

Generate images from text prompts using Chinese image models such as Seedream, Hunyuan Image, and CogView, returning URLs for the requested model and prompt.

Instructions

Generate images with a Chinese image model (Seedream, Hunyuan Image, CogView, Wan...).

Args: model: image model id (e.g. doubao-seedream-5.0, cogview-3-flash). prompt: image description. Returns a list of generated image URLs. Billed per image: check novai_pricing_feed for the per-image price before calling. For chat use novai_chat instead.

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": {
      "model": "<model>",
      "prompt": "<prompt>"
    },
    "name": "novai_generate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYes
promptYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does meaningfully well: it reveals the cost model ('Billed per image'), points to a pricing tool for the exact amount, and states the return shape (list of image URLs). It omits moderation/content-policy behavior and any rate or quota limits, which keeps it from a 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?

Front-loaded with the capability, then parameters, then return value, then cost caveat and the sibling alternative — no filler sentences. The docstring-style 'Args:' block mildly duplicates what the schema already lists, but the added examples justify it.

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?

An output schema exists, so the brief return-value note is sufficient, and both required parameters are covered. For a simple two-parameter generation tool the description is nearly complete; only model-selection guidance and any size/style options are unaddressed.

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 0% (both properties are bare strings), so the description must compensate, and it does: 'model' is explained as an image model id with two concrete examples ('doubao-seedream-5.0, cogview-3-flash') and 'prompt' as the image description. It does not describe acceptable prompt length, aspect ratio, or model-specific constraints.

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') and names the concrete model families (Seedream, Hunyuan Image, CogView, Wan), so an agent knows exactly what capability this exposes. It also explicitly distinguishes itself from the chat sibling ('For chat use novai_chat instead').

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 clear routing guidance away from novai_chat and instructs the agent to check novai_pricing_feed for per-image price before calling. It stops short of saying when to prefer one image model over another or when not to generate images at all, but the key alternative is named.

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