Sceneplane

Create project

project_create

Create a project from a template. Choose executionEngine=ngplant for plants and procedural vegetation; use vegetation_create/edit to author its native model, while Blender packages standard previews and exports. Blender is the default for other scenes. Returns a stable liveUrl for signed-in users to watch job progress and completed previews, plus a durable job handle. Share the returned liveUrl with the user immediately as a clickable Markdown link in a progress message, before waiting for initialization or building the scene. Use the exact returned URL and mention that sign-in is required. Do not wait until the final render; an empty project shows progress before its first preview exists. Poll job_get — the first immutable revision exists once the job completes. template=empty skips preview generation by default, because an empty scene's preview is a 132-byte GLB of nothing and a blank thumbnail; generatePreview overrides that in either direction.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes	Human-readable name for the new project.
`template`	No	Initial scene template; empty starts without geometry.	empty
`idempotencyKey`	Yes	Stable caller-chosen key for safe retries of this same request.
`executionEngine`	No	Use ngplant for plants/vegetation; Blender packages standard outputs. Default blender preserves ordinary scene authoring.	blender
`generatePreview`	No	Render the preview GLB and 384px thumbnail for the first revision. Defaults to TRUE for templates that place geometry or lights and FALSE for template=empty, whose preview is a 132-byte GLB of nothing plus a blank thumbnail. Pass it explicitly to override either default.

Output Schema

TableJSON Schema

Name	Required	Description
`job`	Yes
`liveUrl`	Yes	Stable project preview page. Share this URL with the user immediately as a clickable link; requires sign-in and organization membership.
`projectId`	Yes	Stable project ID returned by project_create or projects_list.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 1, 2026

addedInput schema / properties / executionEngine

Added value: +{
+  "default": "blender",
+  "description": "Use ngplant for plants/vegetation; Blender packages standard outputs. Default blender preserves ordinary scene authoring.",
+  "enum": [
+    "blender",
+    "ngplant"
+  ],
+  "type": "string"
+}

Changed1 schema field changedSep 30, 2026

changedInput schema / properties / template / enum

Previous value: -[
-  "empty",
-  "product_studio",
-  "three_point_lighting",
-  "low_poly",
-  "print_ready"
-]New value: +[
+  "empty",
+  "product_studio",
+  "three_point_lighting",
+  "low_poly",
+  "print_ready",
+  "starter_planter",
+  "starter_crate",
+  "starter_scale_block"
+]

First observedSep 24, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only carry the safety profile (not read-only, not idempotent-hinted); the description goes far beyond by disclosing the return contract (stable liveUrl plus durable job handle), the sign-in requirement, the polling path via job_get, and the first-immutable-revision timing. This is exactly the behavioral context that structured fields do not supply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: purpose first, then engine guidance, then the return/workflow contract. It runs long and mixes invocation guidance with agent workflow instructions, so some sentences could be trimmed, but each carries distinct information rather than filler.

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?

For a creation tool with an output schema, annotations, and five enum-heavy parameters, the description covers purpose, alternatives, engine semantics, return values, the required sharing step, and polling. Nothing an agent needs to call it correctly is missing.

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 adds real meaning on top: the ngplant-vs-Blender tradeoff for executionEngine and the true/false defaults for generatePreview that depend on the template, plus the rationale for template=empty. It augments rather than repeats the schema.

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?

States a specific verb and resource ('Create a project from a template') and immediately frames the engine choice with sibling tools ('vegetation_create/edit to author its native model'). An agent can route this against project_update, scene_apply, and the vegetation tools without opening a 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?

Explicit selection rules: executionEngine=ngplant for plants/procedural vegetation, vegetation_create/edit for the native model, Blender as default for other scenes. It also names the when-not condition for preview generation on template=empty. That is genuine when/when-not/alternatives guidance.

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

All Sceneplane tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?