Skip to main content
Glama

ai_modeling_brush_paint

Paint colors or projected images onto 3D models with world-space brush strength and hardness; fill or erase parts, undo/redo edits, and bake textures for retexture-apply.

Instructions

paint colors or projected images with world-space brush strength/hardness, fill parts, erase to source, and undo/redo; bake textures for retexture-apply

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>",
      "actions": "<actions>"
    },
    "name": "ai_modeling_brush_paint"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionsYes
model_pathYesExact original textured GLB used by this edit history.
history_pathNoPrior brush-paint manifest; source and image hashes are checked before replay.
destination_pathYesNew JSON manifest; sibling .assets directory holds textures and preview GLB.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, and the description is consistent with that by implying output goes to a new destination. It adds genuinely useful behavior beyond the annotations: strokes are world-space with strength/hardness, erase returns to source, and undo/redo/reset are available within the same call. It does not explain that history_path replays a prior manifest with hash verification, nor what the resulting manifest/preview contains, which are the traits an agent would most need.

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?

It is a single dense sentence with semicolon-separated clauses, front-loaded with the primary painting actions, which is reasonably efficient. The final clause about baking textures is cryptic and arguably belongs to a different tool, and the slash-separated phrasing ('strength/hardness', 'undo/redo') compresses distinct concepts. Compact, but some phrasing does not earn its place.

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?

This is a complex tool: a 128-item actions array with five action variants plus three path parameters, and no output schema. The description conveys the action families and the world-space painting model, but says nothing about how actions compose within one call, how history replay interacts with destination_path, or what the caller receives. The rich schema absorbs much of the burden, so the description is adequate rather than complete.

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 75%, so the schema already documents model_path, history_path, destination_path, size, points and hardness. The description adds some mapping value by naming the resource kinds (solid color vs projected image) and the fill-parts and undo/redo action families, which helps the agent pick the right action variant. It adds no detail on ordering, accumulation, or limits of the actions array beyond what the schema states.

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

Purpose3/5

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

The description enumerates concrete verbs and resources (paint colors or projected images, fill parts, erase to source, undo/redo), so the agent knows it is a brush-editing tool. However, the trailing clause 'bake textures for retexture-apply' introduces a second, vaguely-scoped capability that overlaps conceptually with the sibling ai_modeling_brush_bake, and no sibling is named to disambiguate. The result is a recognizable but muddy purpose statement for a multi-action tool.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no when-not-to-use guidance, and no reference to alternatives such as ai_modeling_brush_bake, ai_modeling_brush_parts, ai_modeling_brush_pick or ai_modeling_brush_snapshot. The agent must infer from the action list alone which sibling handles baking, part queries, or picking. Only the implicit signal that this tool handles strokes/fills/erase/undo counts as guidance.

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