novelai

Overview Schema Source Related Servers Discussions Admin

novelai_create_mask

Creates a local infill mask at the source image size, using white to repaint and black to keep; supports rectangle, ellipse, and polygon regions with optional feathering and saves a new PNG.

Instructions

Create a local infill mask at the source image size. White repaints; black keeps. Supports rectangles, ellipses and polygons in pixel coordinates, plus optional feathering. Saves a new PNG; no network request.

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": {
      "image_path": "<image_path>",
      "regions": "<regions>"
    },
    "name": "novelai_create_mask"
  }
}

Input Schema

Name	Required	Description	Default
`feather`	No
`regions`	Yes
`image_path`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 21, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-idempotent, non-open-world write. The description adds real context beyond that: it writes a new PNG to disk, performs no network request, and explains mask semantics (white repaints, black keeps). It still does not say whether an existing file is overwritten or where the output lands.

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?

Four tight sentences, front-loaded with the action and scope, then the color convention, supported shapes, and side effect. No filler or repetition of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should account for the return artifact; 'Saves a new PNG' gestures at it but gives no path or naming, and nothing is said about overwrite behavior. For a file-writing tool with 0% schema coverage this leaves an agent with open questions before calling.

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

Parameters3/5

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

Schema description coverage is 0%, so the description carries the burden. It usefully explains the shape vocabulary (rectangle/ellipse/polygon), that coordinates are in pixels, and that feathering is optional, but it never explains image_path, the box-vs-points distinction, or the feather default/minimum.

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 ('Create a local infill mask') plus scope ('at the source image size') and the color convention ('White repaints; black keeps'). The 'local ... no network request' framing distinguishes it from the network-bound siblings like novelai_generate and novelai_upscale.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used to build a mask for a subsequent infill/repaint step, and clarifies it is local rather than a network call, but it never names an alternative tool or states when-not to use it. Usage is inferable but not explicit.

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

Deploy Server