Skip to main content
Glama

Multipass 3D scene (SSAO + depth)

multipass_3d_depth

Creates a 3D scene with SSAO for contact shadows and exposes a depth map for synthetic depth effects like displacement or silhouette.

Instructions

Build a renderable 3D scene with depth cues that read on stage: a Geometry COMP holding the chosen primitive (sphere/box/torus/grid), a Camera, a Light, and a Render TOP beauty pass, output as a Null — like create_3d_scene but with an optional Screen-Space Ambient Occlusion (SSAO) pass for contact shadows, and an optional Depth TOP output. The SSAO TOP is wired directly after the Render TOP (it needs the depth buffer — no TOP between them) and combined with the color. When expose_depth is on, a Depth TOP resolves the same render into a depth map exposed as a second Null ('depth_out'); feed that path into create_depth_displacement or create_depth_silhouette with source='existing_top' for a synthetic depth-driven effect — no depth camera needed. Optionally GPU-instanced into a grid, with spin over time. Exposes Spin, Zoom, and (with SSAO) an Ssao toggle. Returns a summary plus a JSON block with the container path, created node paths, the render/output/depth paths, exposed controls, node errors, warnings, and an inline preview image.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoName of the self-contained container created under parent_path.multipass_3d
parent_pathNoParent COMP path the multipass 3D container is created inside (default '/project1')./project1
geometryNoPrimitive to render.torus
instancesNoGPU-instanced copies scattered over a grid (1 = single).
ssaoNoAdd a Screen-Space Ambient Occlusion pass for contact shadows/depth.
expose_depthNoExpose a Depth TOP output (feeds create_depth_displacement/silhouette synthetically).
spinNoDegrees/sec rotation.
resolutionNoRender resolution [width, height] in pixels.
Behavior4/5

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

Annotations already indicate non-read-only, non-destructive, open-world. Description adds detail on wiring order (SSAO after Render, no TOP between), exposed controls (Spin, Zoom, Ssao toggle), and return value structure (summary + JSON block with paths, errors). Does not mention potential side effects or performance impact.

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 description is relatively long but well-structured: main purpose, comparison, wiring details, parameter hints, and return info. Each sentence serves a purpose, though some details could be more concise. Front-loaded with key purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 8 parameters and no output schema, the description covers creation steps, parameter roles, wiring constraints, and return format (summary + JSON). It lacks an explicit list of return fields but is sufficient for an agent to use the tool 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?

Input schema provides 100% description coverage, so baseline is 3. The description adds context for 'expose_depth' (its purpose for downstream tools) and 'ssao' (for contact shadows). This extra clarity warrants a 4.

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?

The description clearly states the tool builds a 3D scene with specific components (Geometry, Camera, Light, Render TOP) and optional SSAO and Depth outputs. It explicitly compares to sibling 'create_3d_scene', providing distinct purpose.

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?

The description explains when to use this tool over the sibling 'create_3d_scene' (for SSAO/depth), and provides downstream usage hints for depth output with 'create_depth_displacement' or 'create_depth_silhouette'. It also notes that no depth camera is needed.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Pantani/tdmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server