describe_scene
One-call orientation for the OPEN scene (works in edit and play mode): total/root object counts, component histogram (top 20 types), every camera with position, light count, tag histogram (top 12), and the aggregate world bounds of renderable content. Returns a structured summary — orient here, t...
This record as markdown: /tools/sbox/describe-scene.md
What describe_scene does on Sbox
AI agents call describe_scene to retrieve information from Sbox without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why describe_scene is rated Low
Tool queries scene data without modifying or executing any game logic or commands.
From the tool's definition describe_scene, one-call orientation, returns structured summary, read-only
Risk signalsBulk/mass operation — affects multiple targets · Admin/system-level operation
Attacks that exploit this kind of access
The rule that runs describe_scene safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sbox, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For describe_scene, this is the rule to start with:
describe_scene is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Sbox, apply this rule, and every describe_scene call is checked against it from then on.
Questions about describe_scene
One-call orientation for the OPEN scene (works in edit and play mode): total/root object counts, component histogram (top 20 types), every camera with position, light count, tag histogram (top 12), and the aggregate world bounds of renderable content. Returns a structured summary — orient here, then find_objects by component/tag, get_scene_hierarchy for structure, find_broken_references for health, screenshot_orbit to look at something. Complements describe_project (project-level). Read-only. It is categorised as a Read tool in the Sbox MCP Server, which means it retrieves data without modifying state.
Register the Sbox MCP server in PolicyLayer and add a rule for describe_scene: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sbox. Nothing to install.
describe_scene is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the describe_scene rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for describe_scene. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
describe_scene is provided by the Sbox MCP server (sbox-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sbox, and thousands of servers like it.
This server
Across the catalogue