Skip to main content
Glama

ai_modeling_brush_bake

Project an image or color onto a 3D model via a camera and bake it into textures, using screen-space stroke selections to target surfaces.

Instructions

project an image or color through a camera with legacy screen-space selection; use brush-paint for world-space brush strength and hardness

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_path": "<model_path>",
      "destination_path": "<destination_path>",
      "camera_matrix": "<camera_matrix>"
    },
    "name": "ai_modeling_brush_bake"
  }
}

Input Schema

NameRequiredDescriptionDefault
fovNo
colorNo
opacityNo
strokesNoLegacy screen-space selection, origin top-left; empty selects all front-facing surfaces. Use brush-paint for the webpage world-space brush and hardness.
image_pathNo
model_pathYes
part_namesNo
model_sha256No
camera_matrixYes
destination_pathYesOutput JSON manifest; sibling .assets directory contains part textures and preview GLB.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

C2.8/5.0
Behavior2/5

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

Annotations already declare a non-read-only, open-world, non-destructive operation, so safety is partially covered. The description adds nothing about the fact that this writes files (a JSON manifest plus an .assets directory with part textures and a preview GLB – only visible in the schema's destination_path description), nor about overwrite behavior, existing texture replacement, or cost/duration of a bake. For a file-producing geometry operation that is a real gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Very short and front-loaded, with no filler sentences. But the compression comes at the cost of clarity: 'legacy screen-space selection' and the semicolon-joined sibling reference read as terse shorthand rather than a self-contained explanation.

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

Completeness2/5

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

Ten parameters, three required, no output schema, and side effects on disk make this a complex tool. The description does not explain the produced artifacts, how part_names interacts with strokes, or what happens when both color and image_path are given, so an agent cannot call it confidently from the description alone.

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

Parameters2/5

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

Schema description coverage is only 20% across 10 parameters, so the description is expected to compensate. It hints at camera_matrix, image_path/color, and strokes, but says nothing about fov, opacity, part_names, model_sha256, or the semantics of image-vs-color precedence, leaving most parameters undocumented in either place.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete operation (projecting an image or color through a camera onto a model) plus the selection mechanism (legacy screen-space strokes), which is enough to distinguish it from ai_modeling_brush_paint. It stops short of explicitly framing the operation as a texture bake that produces output artifacts, leaving the tool name to carry that meaning.

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?

It names one alternative and the condition that selects it (brush-paint for world-space strength/hardness), which is genuine routing guidance. However, it never states when to choose this tool – e.g. baking a projected image onto surfaces rather than painting interactively – so the agent must infer the positive case.

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

Deploy Server

Other Tools