save_voxel_modelSave the temporary model identified by modelRef to private VoxelDraft Cloud Projects. Requires project-write OAuth scope. Pass projectId to update an existing owned cloud project.
| Name | Required | Description | Default |
|---|---|---|---|
| modelRef | Yes | Short temporary VoxelDraft model reference returned by model tools | |
| projectId | No |
Changes observed during successful MCP inspections.
Input schema / properties / modelRef / descriptionPrevious value: -"Short temporary VoxelDraft model reference that expires after 7 days of inactivity"New value: +"Short temporary VoxelDraft model reference returned by model tools"Output schema / (root)Previous value: -{
- "additionalProperties": false,
- "properties": {
- "editUrl": {
- "format": "uri",
- "type": "string"
- },
- "modelRef": {
- "description": "Short temporary VoxelDraft model reference that expires after 7 days of inactivity",
- "maxLength": 64,
- "type": "string"
- },
- "project": {
- "additionalProperties": false,
- "properties": {
- "byte_size": {
- "minimum": 0,
- "type": "integer"
- },
- "created_at": {
- "minimum": 0,
- "type": "integer"
- },
- "id": {
- "type": "string"
- },
- "name": {
- "type": "string"
- },
- "updated_at": {
- "minimum": 0,
- "type": "integer"
- },
- "voxel_count": {
- "minimum": 0,
- "type": "integer"
- }
- },
- "required": [
- "id",
- "name",
- "voxel_count",
- "byte_size",
- "created_at",
- "updated_at"
- ],
- "type": "object"
- },
- "renderUrl": {
- "format": "uri",
- "type": "string"
- },
- "saved": {
- "const": true,
- "type": "boolean"
- }
- },
- "required": [
- "saved",
- "project",
- "modelRef",
- "editUrl",
- "renderUrl"
- ],
- "type": "object"
-}New value: +nullInput schema / properties / modelRemoved value: -{
- "type": "string"
-}Input schema / properties / modelRefAdded value: +{
+ "description": "Short temporary VoxelDraft model reference that expires after 7 days of inactivity",
+ "maxLength": 64,
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "model"
-]New value: +[
+ "modelRef"
+]Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": false,
+ "properties": {
+ "editUrl": {
+ "format": "uri",
+ "type": "string"
+ },
+ "modelRef": {
+ "description": "Short temporary VoxelDraft model reference that expires after 7 days of inactivity",
+ "maxLength": 64,
+ "type": "string"
+ },
+ "project": {
+ "additionalProperties": false,
+ "properties": {
+ "byte_size": {
+ "minimum": 0,
+ "type": "integer"
+ },
+ "created_at": {
+ "minimum": 0,
+ "type": "integer"
+ },
+ "id": {
+ "type": "string"
+ },
+ "name": {
+ "type": "string"
+ },
+ "updated_at": {
+ "minimum": 0,
+ "type": "integer"
+ },
+ "voxel_count": {
+ "minimum": 0,
+ "type": "integer"
+ }
+ },
+ "required": [
+ "id",
+ "name",
+ "voxel_count",
+ "byte_size",
+ "created_at",
+ "updated_at"
+ ],
+ "type": "object"
+ },
+ "renderUrl": {
+ "format": "uri",
+ "type": "string"
+ },
+ "saved": {
+ "const": true,
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "saved",
+ "project",
+ "modelRef",
+ "editUrl",
+ "renderUrl"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and non-read-only, so the safety profile is partly covered. The description adds genuinely useful behavior the annotations don't carry: the required OAuth scope and the ownership constraint on updating a project. It still doesn't say that an existing project's contents are overwritten, which is the main residual gap for a destructive write.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with the core action front-loaded, followed by the permission requirement and the optional upgrade path. Every clause carries information; nothing is padding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter, no-output-schema tool this covers the essentials: what is saved, where, the auth requirement, and what projectId changes. The one meaningful omission is the consequence of saving into an existing project (overwrite vs. merge), which matters given the destructive hint.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 50% (projectId has no schema description), and the description compensates by explaining exactly what projectId does – updating an existing owned cloud project – and by characterizing modelRef as a temporary reference from model tools. This adds meaning the schema alone does not provide.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb ('Save') plus a precise resource ('the temporary model identified by modelRef') and destination ('private VoxelDraft Cloud Projects'), which makes its role among the save/create/edit/export/render siblings reasonably evident. It stops short of explicitly contrasting itself with a named sibling, so it lands just below the top tier.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states a clear precondition ('Requires project-write OAuth scope') and a conditional branch: pass projectId to update an existing owned project, omit it to create a new one. That is real when-to-use guidance, though it names no alternative tool for the cases this one doesn't cover.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.