Skip to main content
Glama

Generate 3D Model

sirv_generate_3d_model

Generate a 3D model from a single product photo for 3D viewers and AR, with selectable topology, PBR textures, and target polygon count.

Instructions

Make a 3D model from one product photo in image_url.

Use it for 3D viewers and AR. Do not use it to make an existing GLB file smaller (use sirv_optimize_glb) or for a depth image only (use sirv_generate_depth_map).

Inputs: model defaults to meshy. topology and target_polycount (default 30000) work with meshy and meshy-multi. enable_pbr works with meshy, meshy-multi and hunyuan3d. The other models ignore them.

Returns model_url (the main file), the other formats by file type, and a thumbnail URL. The request can take up to 20 minutes: keep the connection open for that long.

Credits: spends workspace credits. The cost depends on the model and options.

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_url": "<image_url>"
    },
    "name": "sirv_generate_3d_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo3D model generator. Default: meshymeshy
topologyNoMesh faces: triangle or quad. Default: triangletriangle
image_urlYesPublic URL of the product photo
enable_pbrNotrue adds PBR (physically based rendering) textures. Default: true
target_polycountNoPolygons to aim for, 1000 to 200000. Default: the model's own

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only say it is a non-readonly, non-destructive, open-world, non-idempotent call. The description adds information annotations cannot convey: the call spends workspace credits with variable cost, it can run up to 20 minutes and the connection must stay open, and it returns a main model file plus per-format files and a thumbnail. That is exactly the extra context needed to decide whether to attempt it.

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?

Purpose and exclusions are front-loaded, then inputs, then return values, then cost and latency. Each line carries a distinct decision-relevant fact with no restatement of the name or title.

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

Completeness5/5

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

With no output schema, the description carries the return-value burden and does so (model_url, per-format files, thumbnail). For a paid, long-running, generative tool it covers the three things an agent needs before calling: cost, duration, and connection requirement.

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 above baseline by documenting a cross-parameter compatibility matrix the schema cannot express: topology and target_polycount apply only to meshy and meshy-multi, enable_pbr applies to meshy, meshy-multi and hunyuan3d, and the other models silently ignore them. One flaw keeps it from 5: it says target_polycount defaults to 30000 while the schema says 'the model's own' default, a discrepancy an agent may trip on.

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 opening line states a specific verb and resource plus its input source: 'Make a 3D model from one product photo in `image_url`.' It immediately distinguishes itself from the two closest siblings (GLB optimization and depth-map generation), so an agent can select it 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 Guidelines5/5

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

It gives an affirmative use case ('3D viewers and AR') and two explicit exclusions with named alternatives: use sirv_optimize_glb to shrink an existing GLB, use sirv_generate_depth_map for a depth image only. That is when-to-use, when-not-to-use, and alternatives all in one place.

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