Skip to main content
Glama

Add something to an R3 project

r3_factory_run

Add an object to an existing R3 project — a cube, sphere, terrain, lighting, a physics body, and so on. Each factory builds a complete, correctly-wired object (mesh + geometry + material + colour, already connected), so you never assemble components by hand. Kept at once in the project's live copy: every R3 tab with the project open shows it now, no editor needed and nothing to save (r3_editor_create is the same tool). The answer says what was kept and its seq. "name" names what you make ("Leg front left" → entityRef leg_front_left): the primary component (a cube's Mesh, a light), unique in the project (a name already used gets _2); its geometry and material take it too (leg_front_left_geometry, leg_front_left_material). Name parts when you make them (a later rename: r3_component_rename). "StudioLighting" lights a scene the way a photo studio does: one of R3's built-in HDR environments (studio, sunset, sky) as the scene's environment, so metal and glossy materials reflect, plus a key light. Use r3_factory_list to see the factories and their options.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>",
      "factory": "<factory>"
    },
    "name": "r3_factory_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe name of what you make, e.g. "Leg front left" (at most 120 characters). Its entityRef, the name code uses, follows from it (leg_front_left).
paramsNoFactory options, e.g. {"color": 16711680, "position": {"y": 2}}. Every option has a default. Color is a packed RGB integer. Rotations are in RADIANS, not degrees: a quarter turn is Math.PI/2 ≈ 1.5708 (the R3 Inspector shows rotations in degrees: 90°).
factoryYesFactory name, e.g. "Cube", "Sphere", "PhysicsCube". See r3_factory_list.
projectIdYesThe project to add to, from r3_project_create.

Output Schema

NameRequiredDescriptionDefault
seqNo
rolesYes
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.
createdYes
factoryYes
physicsYes
projectIdYes
componentCountYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / params / description
      Previous value: -"Factory options, e.g. {\"color\": 16711680, \"position\": {\"y\": 2}}. Every option has a default. NOTE: rotation is in RADIANS and color is a packed RGB integer."New value: +"Factory options, e.g. {\"color\": 16711680, \"position\": {\"y\": 2}}. Every option has a default. Color is a packed RGB integer. Rotations are in RADIANS, not degrees: a quarter turn is Math.PI/2 ≈ 1.5708 (the R3 Inspector shows rotations in degrees: 90°)."
  2. Changed1 schema field changed
    • addedInput schema / properties / name
      Added value: +{
      +  "description": "The name of what you make, e.g. \"Leg front left\" (at most 120 characters). Its entityRef, the name code uses, follows from it (leg_front_left).",
      +  "type": "string"
      +}
  3. Changed2 schema fields changed
    • addedOutput schema / properties / physics
      Added value: +{
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "code": {
      +        "type": "string"
      +      },
      +      "collider": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "message": {
      +        "type": "string"
      +      },
      +      "rigidBody": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      }
      +    },
      +    "required": [
      +      "code",
      +      "collider",
      +      "rigidBody",
      +      "message"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "projectId",
      -  "factory",
      -  "created",
      -  "roles",
      -  "componentCount",
      -  "answer"
      -]New value: +[
      +  "projectId",
      +  "factory",
      +  "created",
      +  "roles",
      +  "physics",
      +  "componentCount",
      +  "answer"
      +]
  4. Changed1 schema field changed
    • addedOutput schema / properties / roles / additionalProperties / properties / readThrough
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "entityRef": {
      +      "type": "string"
      +    },
      +    "property": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "entityRef",
      +    "property"
      +  ],
      +  "type": "object"
      +}
  5. 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",
      -  "factory",
      -  "created",
      -  "roles",
      -  "componentCount"
      -]New value: +[
      +  "projectId",
      +  "factory",
      +  "created",
      +  "roles",
      +  "componentCount",
      +  "answer"
      +]
  6. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing that the object lands in the project's live copy, that every open R3 tab shows it immediately, and that there is nothing to save and no editor required. It also explains automatic name de-duplication (a reused name gets _2) and that the response reports what was kept plus its seq — meaningful behavior for a non-idempotent, non-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.

Conciseness4/5

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

Front-loaded with the core action, and each sentence carries information. It is dense and single-paragraph, and the StudioLighting explanation is unusually detailed for one factory among many, costing some economy, though it is not 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?

With a full output schema the description needn't document return shape, and it still summarizes it (kept object plus seq). Combined with the live-copy behavior, naming rules, and factory discovery pointer, an agent has everything needed to call this correctly.

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 baseline is 3, but the description adds real meaning: how "name" is transformed into an entityRef, that the primary component is the one named while geometry and material inherit suffixed names, and why naming at creation matters. It doesn't add to the params or projectId semantics beyond 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 ("Add an object to an existing R3 project") and immediately enumerates what can be made (cube, sphere, terrain, lighting, physics body). It also differentiates itself from siblings by noting r3_editor_create is the same tool and that r3_factory_list enumerates the factory set.

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?

Gives clear routing: use r3_factory_list to see factories and their options, and use r3_component_rename for later renames. It also clarifies the alias relationship with r3_editor_create, which prevents duplicate selection. It doesn't explicitly contrast with r3_component_add or r3_editor_add_component, so the exclusion side is incomplete.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources