trident-mcp

Overview Schema Source Related Servers Score Discussions Admin

convert_format

Convert a 3D model to GLTF, FBX, OBJ, STL, USDZ, or 3MF by specifying the original task ID and output format.

Instructions

Convert a generated 3D model to a different file format (GLTF, FBX, OBJ, STL, USDZ, 3MF). This is an async operation — use task_status to poll progress, then download_model to retrieve the converted file.

Input Schema

TableJSON Schema

Name	Required	Description
`bake`	No	Bake material textures during conversion
`quad`	No	Convert to quad mesh output when supported
`format`	Yes	Desired output format: GLTF, FBX, OBJ, STL, USDZ, or 3MF
`packUV`	No	Pack UVs during conversion
`faceLimit`	No	Target face count for converted output
`fbxPreset`	No	FBX preset when exporting FBX, such as unity or unreal
`partNames`	No	Specific segmented part names to export
`scaleFactor`	No	Scale multiplier for converted output
`textureSize`	No	Target texture size for converted output
`textureFormat`	No	Texture image format, such as png, jpg, or webp
`originalTaskId`	Yes	Task ID of the model to convert
`exportOrientation`	No	Target export orientation: +x, -x, +y, or -y. x_up and y_up are accepted as aliases
`exportVertexColors`	No	Export vertex colors when supported
`pivotToCenterBottom`	No	Move pivot to the model center-bottom

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes
`taskId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv0.3.0Jul 11, 2026

addedInput schema / properties / bake

Added value: +{
+  "description": "Bake material textures during conversion",
+  "type": [
+    "null",
+    "boolean"
+  ]
+}

addedInput schema / properties / exportOrientation

Added value: +{
+  "description": "Target export orientation: +x, -x, +y, or -y. x_up and y_up are accepted as aliases",
+  "type": "string"
+}

addedInput schema / properties / exportVertexColors

Added value: +{
+  "description": "Export vertex colors when supported",
+  "type": [
+    "null",
+    "boolean"
+  ]
+}

addedInput schema / properties / faceLimit

Added value: +{
+  "description": "Target face count for converted output",
+  "type": "integer"
+}

addedInput schema / properties / fbxPreset

Added value: +{
+  "description": "FBX preset when exporting FBX, such as unity or unreal",
+  "type": "string"
+}

addedInput schema / properties / packUV

Added value: +{
+  "description": "Pack UVs during conversion",
+  "type": [
+    "null",
+    "boolean"
+  ]
+}

addedInput schema / properties / partNames

Added value: +{
+  "description": "Specific segmented part names to export",
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "null",
+    "array"
+  ]
+}

addedInput schema / properties / pivotToCenterBottom

Added value: +{
+  "description": "Move pivot to the model center-bottom",
+  "type": [
+    "null",
+    "boolean"
+  ]
+}

addedInput schema / properties / quad

Added value: +{
+  "description": "Convert to quad mesh output when supported",
+  "type": [
+    "null",
+    "boolean"
+  ]
+}

addedInput schema / properties / scaleFactor

Added value: +{
+  "description": "Scale multiplier for converted output",
+  "type": "number"
+}

addedInput schema / properties / textureFormat

Added value: +{
+  "description": "Texture image format, such as png, jpg, or webp",
+  "type": "string"
+}

addedInput schema / properties / textureSize

Added value: +{
+  "description": "Target texture size for converted output",
+  "type": "integer"
+}

First observedApr 15, 2026

TDQS

A4/5.0

Behavior3/5

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

The description reveals that the operation is async and guides the user to use task_status and download_model. However, it does not disclose other behavioral traits such as whether the operation is destructive (e.g., whether the original model is modified), rate limits, or authentication requirements. Given that annotations are missing, the description carries the full burden but falls short of complete transparency.

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 include the main purpose, supported formats, and async workflow. Every sentence adds value with no redundant information.

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?

Given the tool's complexity (14 parameters, async behavior) and the existence of an output schema, the description provides sufficient context for the high-level flow (convert, poll, download). It could be slightly more explicit about the return value type (task ID), but overall it is complete enough for an agent to use correctly.

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%, meaning all 14 parameters are already documented in the input schema. The description adds no extra meaning beyond the schema, so it meets the baseline expectation but does not exceed it.

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 specific verb (convert) and resource (3D model), lists the supported output formats, and distinguishes from sibling tools like image_to_3d or import_model by focusing on format conversion. It is specific and unambiguous.

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?

The description provides clear context for when to use this tool (after having a generated 3D model) and explains the async workflow with steps for polling and downloading. However, it does not explicitly state when not to use it or compare with alternatives like text_to_3d, which is a minor omission.

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