Skip to main content
Glama
Sign In
HF Assets

HF Assets

by IvanGlazyrin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Generate a 3D mesh

generate_mesh

Convert an image into a raw 3D mesh: trellis yields a textured GLB, hunyuan an untextured shape; each run writes the GLB plus JSON sidecar metadata.

Instructions

Turn an image into a raw 3D mesh. trellis gives a textured GLB at ~30k faces; hunyuan gives an untextured shape at ~450k faces. Writes the GLB and a .json sidecar with the parameters, the inputs and the raw Space response.

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": "<image>"
    },
    "name": "generate_mesh"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoSeed; change it for another take.
imageYesThe source image, as a path.
modelNoWhich Space to use.trellis
out_dirNoWhere to write the GLB.out/mesh
extra_viewsNoMore views of the same object, fused as multi-image conditioning.

Output Schema

NameRequiredDescriptionDefault
logYesWhat the engine printed while it worked.
filesYesEverything that was written.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and it does well: it discloses that it writes a GLB plus a .json sidecar containing the parameters, inputs, and raw Space response, which is exactly the side-effect information an agent needs. It omits runtime/cost expectations (a 450k-face generation is presumably slow) and whether existing files in out_dir are overwritten.

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?

Three short sentences with zero waste: purpose first, model trade-off second, artifacts written third. Every sentence earns its place and the information is front-loaded.

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?

Output schema exists, so return values need not be described, and the sidecar/GLB output is covered along with the two backend choices. The remaining gap is operational — long-running generation, failure modes, and file-overwrite behavior — which for a file-writing generation tool would be worth one more sentence.

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 the baseline is 3, but the description earns more by explaining the 'model' enum substantively — trellis yields a textured low-poly GLB, hunyuan an untextured high-poly shape — which the schema's terse 'Which Space to use' does not convey. It adds little for seed, out_dir, or extra_views beyond the schema text.

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?

The first sentence names a specific verb and transformation ('Turn an image into a raw 3D mesh'), and the word 'raw' implicitly places it before render_mesh in the pipeline. It does not explicitly name a sibling as an alternative, so it falls short of the 5 bar for sibling differentiation.

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?

There is no explicit when-to-use statement or exclusion relative to siblings like render_mesh or generate_image. However, the trade-off between the two backends ('textured GLB at ~30k faces' vs 'untextured shape at ~450k faces') conveys implied guidance for choosing a model, which is more than nothing.

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