VoxelDraft – AI Voxel Modeling

Create voxel model

create_voxel_model

Read-only

Create an editable VoxelDraft model from a compact, token-efficient instruction stream. This is a stateless computation: it returns an opaque model handle but does not save anything to an account. Use VoxelDraft's compact instruction stream instead of emitting one JSON object per voxel. Coordinates are integers 0..63. Colors are either #RRGGBB or a zero-based palette index. Commands: ["box",x1,y1,z1,x2,y2,z2,color,hollow?] ["ellipsoid",cx,cy,cz,rx,ry,rz,color,hollow?] ["cylinder","x"|"y"|"z",x,y,z,radius,height,color,hollow?] ["line",x1,y1,z1,x2,y2,z2,color] ["roof","x"|"z",x1,y1,z1,x2,y2,z2,color] (gable roof, axis is ridge direction) ["runs","x"|"y"|"z",color,[[x,y,z,length],...]] (preferred exact/freeform representation) ["points",color,[[x,y,z],...]] (sparse details only) ["erase",x1,y1,z1,x2,y2,z2] ["recolor",fromColor,toColor] ["copy",x1,y1,z1,x2,y2,z2,dx,dy,dz] ["repeat",x1,y1,z1,x2,y2,z2,dx,dy,dz,count] ["mirror","x"|"y"|"z",plane,x1,y1,z1,x2,y2,z2] (plane is a grid boundary 0..64) Prefer box/roof/ellipsoid/cylinder for bulk geometry, runs for irregular silhouettes, repeat/mirror for repeated or symmetric parts, and points only for small details. This usually uses far fewer model tokens than raw voxel JSON.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	No
`palette`	No
`commands`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 12, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already state readOnlyHint=true, destructiveHint=false, and openWorldHint=false. The description adds important behavioral context beyond those annotations: this is a stateless computation that returns an opaque handle and does not save to an account. It still does not discuss rate limits or auth, but the key non-persistence behavior is disclosed.

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?

The description is appropriately front-loaded with purpose and the stateless behavior, then provides the command DSL needed to invoke the tool. It is long, but the command list earns its place. One sentence about token savings is somewhat redundant with the earlier instruction-stream rationale.

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?

For a tool with no output schema and sparse annotations, the description gives enough syntax and behavioral context to invoke it correctly, including the command DSL and the fact that it returns an opaque handle. It could be more complete by routing between related creation, editing, saving, and rendering tools.

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 description coverage is 0%, so the description carries the burden. It thoroughly documents the commands parameter, including command forms, coordinate ranges, and color formats, which is the difficult part of the schema. It does not explain the name or palette parameters in comparable detail, but it compensates well overall.

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?

The description states a specific verb and resource: create an editable VoxelDraft model from a compact instruction stream. It also clarifies the output (opaque model handle) and explicitly distinguishes this from persistence by saying it does not save anything to an account.

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 gives clear internal guidance to prefer the compact instruction stream over raw voxel JSON, but it does not explicitly say when to use this tool versus sibling tools like edit_voxel_model, load_voxel_project, or save_voxel_model. The use case is implied rather than routed.

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

All VoxelDraft – AI Voxel Modeling tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?