Skip to main content
Glama
Sign In

R3

by org.r3js
OverviewDiscussionsAdmin

Create an R3 project

r3_project_create

Create a new R3 project and save it to the user's account. Produces a complete, openable project — scene, world, camera, renderer, lighting, audio listener, music transport and OrbitControls (anyone who opens it can turn and zoom the view) — ready for components to be added. Pass template for a phone project (mobile-portrait / mobile-landscape) that fills the screen when published. Returns the project id, which every other project tool takes. r3_whoami confirms which account it is created in.

Input Schema

NameRequiredDescriptionDefault
nameNoProject name, shown in the user's project list. Defaults to "Untitled Project". Max 120 characters.
cameraNoWhere the project's camera starts and what it looks at, e.g. framing a model you add next. Omit it for the default: (0, 5, 10) looking at the origin.
templateNoStart from a project template instead of an Empty Project. "mobile-portrait" — A phone held upright: designed at 390×844 (~19.5:9), fills the screen when published. "mobile-landscape" — A phone held sideways: designed at 844×390 (~19.5:9), fills the screen when published. A template sets the renderer's design size and fullscreen (the canvas fills the screen it runs on; the camera follows the screen's shape, never letterboxed) and the camera's field of view for that orientation. Omit it for an Empty Project, whose renderer also fills the screen (an 800×600 fallback size, the default 75° field of view).

Output Schema

NameRequiredDescriptionDefault
nameYes
answerYesThis answer in words: what was done, what R3 measured, decided or refused, and what to do next. The same text as the result's text block. Read it: the fields beside it are the data, this is the guidance.
templateNo
projectIdYes
environmentYes
componentCountYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / camera
      Added value: +{
+  "additionalProperties": false,
+  "description": "Where the project's camera starts and what it looks at, e.g. framing a model you add next. Omit it for the default: (0, 5, 10) looking at the origin.",
+  "properties": {
+    "lookAt": {
+      "additionalProperties": false,
+      "description": "The point it looks at, e.g. the centre of what you will add.",
+      "properties": {
+        "x": {
+          "type": "number"
+        },
+        "y": {
+          "type": "number"
+        },
+        "z": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "x",
+        "y",
+        "z"
+      ],
+      "type": "object"
+    },
+    "position": {
+      "additionalProperties": false,
+      "description": "Where the camera stands (world units, Y up).",
+      "properties": {
+        "x": {
+          "type": "number"
+        },
+        "y": {
+          "type": "number"
+        },
+        "z": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "x",
+        "y",
+        "z"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "position",
+    "lookAt"
+  ],
+  "type": "object"
+}
  2. Changed2 schema fields changed
    • addedOutput schema / properties / answer
      Added value: +{
+  "description": "This answer in words: what was done, what R3 measured, decided or refused, and what to do next. The same text as the result's text block. Read it: the fields beside it are the data, this is the guidance.",
+  "type": "string"
+}
    • changedOutput schema / required
      Previous value: -[
-  "projectId",
-  "name",
-  "componentCount",
-  "environment"
-]New value: +[
+  "projectId",
+  "name",
+  "componentCount",
+  "environment",
+  "answer"
+]
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say this is a non-read-only, non-idempotent, open-world, non-destructive write. The description goes well beyond that by enumerating exactly what a new project contains (scene, world, camera, renderer, lighting, audio listener, music transport, OrbitControls), what `template` changes about the published result, and what the call returns. That is the kind of context an agent needs before a mutating call with no annotations explaining scope.

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?

Front-loaded with the action and the output, and every clause earns its place. The long parenthetical about OrbitControls is the one patch that could be tightened, and the second sentence is dense with list items.

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 create tool with an output schema, this covers what the agent can't get from structured fields: what a new project contains, what a template does differently, which account it lands in, and what the return id is used for. Nothing needed 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 per field the schema already does the work. The description still adds a reason to pass `template` — that a phone project fills the screen when published — which the enum alone doesn't fully convey. It doesn't add anything about `name` or `camera`, hence 4 rather than 5.

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 new R3 project'), plus where it lands ('save it to the user's account'), which immediately separates it from r3_project_load, r3_project_list and r3_project_delete. No sibling could be confused for this one.

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?

Makes the create-new case explicit and routes the agent to `template` for phone projects and to r3_whoami for account verification. It doesn't state a when-not (e.g. 'use r3_project_load for existing projects'), but the context is clear enough to choose correctly.

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

All R3 toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources