Skip to main content
Glama

scene_state

Read-only

Captures a Roblox Studio camera snapshot of visible objects with world positions and on-screen pixel coordinates, letting you map screenshot pixels to exact 3D locations. Read-only.

Instructions

Spatial snapshot of the scene as the editor camera sees it: camera intrinsics (CFrame, FOV, viewport) + a curated list of visible objects, each with world position/orientation/size AND its on-screen pixel (x,y,depth,onScreen) via WorldToScreenPoint. This is what grounds a screenshot — it lets you say "object X is at screen (px,py) = world (x,y,z)". A Model counts as one object (bounding box); closest objects first. Pair with the official Roblox_Studio MCP's screen_capture. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "scene_state"
  }
}

Input Schema

NameRequiredDescriptionDefault
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
maxDepthNowalk depth (default 2); Models are taken whole
rootPathNoScope the scan (default Workspace)
maxObjectsNodefault 40, capped 120 for transport
nameFilterNosubstring match on Name
classFilterNoIsA class filter, e.g. Model, MeshPart
onScreenOnlyNodefault true — drop objects off-screen / behind camera

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the trailing "Read-only." largely restates that. What it adds beyond structured data is real but limited: ordering semantics (closest objects first), aggregation semantics (a Model counts as one object via its bounding box), and a transport-driven cap. It does not mention cost, latency, or what happens when the scan hits the cap.

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?

The payload description is front-loaded and the four sentences each carry distinct information (what it returns, why it matters, counting semantics, pairing). The quoted example phrase and the trailing "Read-only." are mild padding, but nothing is structurally wasteful.

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?

There is no output schema, so the description must carry the return shape, and it does precisely: camera intrinsics plus per-object world transform and projected pixel with depth and an onScreen flag. Combined with full schema coverage on all 7 optional parameters, an agent has everything needed to call and interpret this tool.

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-parameter defaults and bounds are already carried by the schema. The description still contributes meaning the schema cannot: "A Model counts as one object (bounding box)" clarifies how maxObjects and maxDepth actually count, and "closest objects first" explains which objects survive the maxObjects truncation. That is genuine interpretation guidance rather than repetition.

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?

"Spatial snapshot of the scene as the editor camera sees it" names a concrete resource and the exact vantage point, then enumerates the two payload halves (camera intrinsics: CFrame/FOV/viewport; visible objects with world transform plus WorldToScreenPoint pixel). An agent can distinguish this from get_tree, get_selection, or get_properties without opening the schema.

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?

It states the motivating use case clearly ("what grounds a screenshot", mapping screen pixels to world coordinates) and names a companion tool, screen_capture, for the screenshot half. It stops short of explicit when-not guidance against siblings like get_tree or snapshot, so an agent must infer that this is the camera-relative option rather than the full hierarchy dump.

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