Skip to main content
Glama

blender_process

Run headless Blender operations on local 3D files to prepare Roblox assets: inspect tri limits, decimate to 20k, split by material, fracture, convert formats, or render preview thumbnails.

Instructions

Run a canned headless-Blender operation on a local 3D file (.glb/.gltf/.fbx/.obj/.blend in; .glb/.fbx out — input is never modified). Actions: inspect (Roblox-readiness lint: tri counts vs the 20k limit, materials-per-mesh, UV sets, texture sizes vs the 1024 cap), decimate (reduce to target tris, default 20000), split_by_material (one object per material — Roblox imports one MeshPart per material object), split_chunks (bisect oversized meshes into ≤target-tri pieces), fracture (Cell Fracture shards for destructibles — needs the Cell Fracture extension installed), set_origins (per-object geometry-median origins), convert (re-export, e.g. obj→glb for import_file), downscale_textures (cap textures at texLimit, default 1024), thumbnail (render a 512px PNG preview of the model — SEE an asset before uploading/spending; returned as an image). Needs Blender installed (free) — auto-detected or TUFAN_BLENDER_PATH.

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": {
      "inputFile": "<inputFile>",
      "action": "<action>"
    },
    "name": "blender_process"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesWhich canned operation to run
shardsNoShard count for fracture (default 10)
targetNoTri-count target for decimate/split_chunks (default 20000)
texLimitNoMax texture dimension for downscale_textures (default 1024)
inputFileYesAbsolute path of the local 3D file to process
outputFileNoOutput path (.glb or .fbx). Default: <input dir>/<name>.<action>.glb (inspect: none)
timeoutSecondsNoMax seconds for the Blender run (default 180, max 600)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnly=false, destructive=false, idempotent=false, but the description adds real behavioral detail: the input file is never modified, accepted input/output formats are enumerated, thumbnail returns an image, fracture requires the Cell Fracture extension, and Blender must be installed or TUFAN_BLENDER_PATH set. These are exactly the prerequisites and side-effect boundaries an agent needs.

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 core operation, constraints, and the action list in a single dense paragraph, with zero filler sentences. It is parenthetical-heavy and long enough that scanning for a specific action takes effort, but no sentence is expendable.

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 nine-action tool with no output schema, it covers inputs, outputs, prerequisites, and default paths well, and explicitly documents that thumbnail returns an image. It does not describe what the textual/non-thumbnail actions return (e.g. the inspect lint report shape), which leaves a modest gap.

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 100%, so defaults are already documented, but the description adds role-level meaning: `target` governs decimate and the split_chunks piece size, `texLimit` caps downscale_textures against the 1024 Roblox cap, and `shards` applies only to fracture. It stops short of clarifying timeoutSeconds or the inspect case for outputFile beyond a parenthetical.

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 ("canned headless-Blender operation on a local 3D file") and then enumerates all nine actions with a one-line explanation of each. The word "canned" plus the fixed action enum separates it from an arbitrary-script executor like blender_run, so an agent can route without opening the schema.

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?

Each action carries implied usage context — inspect as a Roblox-readiness lint, thumbnail as a pre-upload preview, convert for preparing obj→glb for import_file. It gives clear context but never states explicit exclusions or names blender_run as the alternative for non-canned work, so a 5 is not warranted.

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