tdmcp

Create depth-driven POP field

create_depth_pop_field

Creates a depth-driven GPU POP scatter field in TouchDesigner, sampling a depth/mask TOP to displace or scatter particles; auto-spins up a depth source when none is specified.

Instructions

Build a depth-driven GPU POP scatter field: consumes a depth/mask TOP and uses lookup_texture_pop to sample depth for displacement/scatter proxies (and optionally color). When depth_top_path is omitted, auto-spins-up a setup_segmentation MediaPipe chain inside the container and uses its mask Null TOP as the depth source. Scatter modes: 'displace' applies a uniform depth-scale proxy, 'emit' adds an emission-like jitter scatter proxy, 'both' does both. Forward-compatible: pass create_depth_from_2d (Depth Anything, W4) output as depth_top_path. NOTE: POPs are Experimental — op types and par names are fail-forward, probe on a live TD. Returns a JSON block with container path, depth source info, controls, warnings, and unverified probe record.

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": "create_depth_pop_field"
  }
}

Input Schema

Name	Required	Description	Default
`name`	No	Name for the self-contained container created under parent_path.	depth_pop_field
`spin`	No	Y-rotation of the field in deg/sec, animated via transformPOP ry expression. Exposed as Spin knob.
`point_size`	No	Render TOP point size, exposed as PointSize knob.
`resolution`	No	Render TOP resolution [width, height].
`depth_scale`	No	Multiplier on the depth-driven displacement amount along +Z for displace/both scatter modes. Exposed as DepthScale knob when that displacement proxy is active.
`parent_path`	No	Parent COMP path where the depth-pop-field container is created.	/project1
`invert_depth`	No	Treat dark as near instead of bright. Implemented via Level TOP invert on a proxy feed.
`scatter_mode`	No	'displace' = uniform depth-scale proxy on the point cloud; 'emit' = emission-like scatter jitter around the sampled depth field; 'both' = depth-scale proxy + scatter jitter. True depth-weighted birth is unverified.	displace
`color_by_depth`	No	When true, copies sampled RGBA into POP Color attribute via a second lookup_texture_pop (near = bright / far = dark).
`depth_top_path`	No	Absolute path of an existing depth/mask TOP (luminance = depth, bright = near by default). When omitted, the tool auto-spins-up a setup_segmentation chain inside the container and uses its mask Null TOP as the depth source. Future W4: pass create_depth_from_2d output here.
`expose_controls`	No	Build the live artist knobs panel for the active depth field controls.
`particle_density`	No	Approximate point count fed to pointgeneratorPOP.numpoints (100–500 000).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.13.1Aug 2, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses side effects: it creates a container, may auto-spin-up a setup_segmentation MediaPipe chain, and returns a JSON block with warnings. It also warns that POPs are experimental and fail-forward, adding risk context not captured by annotations.

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 a single paragraph that packs core purpose, auto-spin behavior, scatter modes, forward-compat, and an experimental warning into a few sentences. It is well-structured and front-loaded, though slightly dense for a 12-param tool.

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?

For a tool with 12 params, no output schema, and no required params, the description covers the essential workflow, input handling, return value, and risk. It doesn't provide examples or prerequisites, but the schema fills the parameter gaps. The openWorldHint and experimental note enhance completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters are documented. The tool description adds minimal parameter-level detail beyond the schema; it mentions scatter modes at a high level but the schema already explains them in comparable detail. Therefore baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Build a depth-driven GPU POP scatter field' – a specific verb and resource. It further clarifies it consumes a depth/mask TOP and uses lookup_texture_pop, distinguishing it from generic POP creation tools, though it doesn't explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the conditional behavior when depth_top_path is omitted vs provided, and mentions forward-compatibility with create_depth_from_2d. However, it does not explicitly specify when to use this tool over sibling tools like create_pop_field or create_gpu_particle_field.

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

Deploy Server