Skip to main content
Glama

text_to_3d

Generate a 3D model from a text prompt. This asynchronous operation returns a task ID to poll for progress and download the result.

Instructions

Generate a 3D model from a text prompt. This is an async operation — use task_status to poll progress and download_model to retrieve the result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pbrNoEnable PBR materials. When true, Tripo will also enable texture output
quadNoGenerate quad mesh output when supported
promptYesText description of the 3D model to generate
textureNoEnable texturing. Set false to request a base model without textures
autoSizeNoAutomatically scale the model to real-world dimensions in meters
compressNoCompression mode. Set to geometry to request geometry compression
exportUVNoControl whether UV unwrapping is performed during generation
faceLimitNoTarget polygon face count
imageSeedNoOptional seed for prompt-to-image generation before 3D reconstruction
modelSeedNoOptional seed for geometry generation
textureSeedNoOptional seed for texture generation
modelVersionNoModel version (e.g. turbo, v3.0, v3.1, p1). Defaults to the latest supported H3 model
smartLowPolyNoEnable Tripo smart low-poly mesh optimization when supported
generatePartsNoGenerate semantic mesh parts when supported
negativePromptNoWhat to avoid in the generation
textureQualityNoTexture quality: standard or detailed
geometryQualityNoGeometry detail mode for H3 models: standard or detailed

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusYes
taskIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changedv0.3.0
    • addedInput schema / properties / autoSize
      Added value: +{
      +  "description": "Automatically scale the model to real-world dimensions in meters",
      +  "type": [
      +    "null",
      +    "boolean"
      +  ]
      +}
    • addedInput schema / properties / compress
      Added value: +{
      +  "description": "Compression mode. Set to geometry to request geometry compression",
      +  "type": "string"
      +}
    • addedInput schema / properties / exportUV
      Added value: +{
      +  "description": "Control whether UV unwrapping is performed during generation",
      +  "type": [
      +    "null",
      +    "boolean"
      +  ]
      +}
    • addedInput schema / properties / generateParts
      Added value: +{
      +  "description": "Generate semantic mesh parts when supported",
      +  "type": [
      +    "null",
      +    "boolean"
      +  ]
      +}
    • addedInput schema / properties / geometryQuality
      Added value: +{
      +  "description": "Geometry detail mode for H3 models: standard or detailed",
      +  "type": "string"
      +}
    • addedInput schema / properties / imageSeed
      Added value: +{
      +  "description": "Optional seed for prompt-to-image generation before 3D reconstruction",
      +  "type": [
      +    "null",
      +    "integer"
      +  ]
      +}
    • addedInput schema / properties / modelSeed
      Added value: +{
      +  "description": "Optional seed for geometry generation",
      +  "type": [
      +    "null",
      +    "integer"
      +  ]
      +}
    • changedInput schema / properties / modelVersion / description
      Previous value: -"Model version (e.g. v2.5, v3.0, v3.1). Defaults to latest"New value: +"Model version (e.g. turbo, v3.0, v3.1, p1). Defaults to the latest supported H3 model"
    • addedInput schema / properties / pbr
      Added value: +{
      +  "description": "Enable PBR materials. When true, Tripo will also enable texture output",
      +  "type": [
      +    "null",
      +    "boolean"
      +  ]
      +}
    • addedInput schema / properties / quad
      Added value: +{
      +  "description": "Generate quad mesh output when supported",
      +  "type": [
      +    "null",
      +    "boolean"
      +  ]
      +}
    • addedInput schema / properties / smartLowPoly
      Added value: +{
      +  "description": "Enable Tripo smart low-poly mesh optimization when supported",
      +  "type": [
      +    "null",
      +    "boolean"
      +  ]
      +}
    • addedInput schema / properties / texture
      Added value: +{
      +  "description": "Enable texturing. Set false to request a base model without textures",
      +  "type": [
      +    "null",
      +    "boolean"
      +  ]
      +}
    • addedInput schema / properties / textureQuality
      Added value: +{
      +  "description": "Texture quality: standard or detailed",
      +  "type": "string"
      +}
    • addedInput schema / properties / textureSeed
      Added value: +{
      +  "description": "Optional seed for texture generation",
      +  "type": [
      +    "null",
      +    "integer"
      +  ]
      +}
  2. First observed

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations provided, the description carries full burden. It discloses the asynchronous nature, which is a key behavioral trait. However, it omits other behavioral details such as required permissions (if any), potential failure modes, or any side effects beyond the async workflow.

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?

The description is extremely concise: two sentences that cover the core purpose and the essential async workflow. Every word adds value, with no redundant or filler content.

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?

Given the complexity (17 parameters) and the existence of an output schema, the description adequately covers the main workflow (async generation). However, it could mention the output (e.g., 'Returns a task ID for polling') or provide a brief example of usage, but the output schema likely covers return values.

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 coverage is 100%, so the schema already documents all parameters with descriptions. The tool description adds no extra parameter information beyond what is in the schema. Baseline of 3 is appropriate since the schema does the heavy lifting.

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 clearly states the action ('Generate a 3D model') and the resource ('from a text prompt'). It also distinguishes itself by noting it's an async operation and points to related tools (task_status, download_model), making its purpose unmistakable even among many siblings.

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?

The description explains the async workflow (poll with task_status and retrieve with download_model), which is helpful context. However, it does not explicitly state when to use this tool versus alternatives like image_to_3d or multiview_to_3d, nor does it mention prerequisites or exclusions.

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