Skip to main content
Glama

Create POP field (GPU points)

create_pop_field

Generate a GPU point field in TouchDesigner with selectable point patterns, animated rotation, and exposed controls for point size and spin speed.

Instructions

Build a GPU point field using TouchDesigner's POP (Point OPerator) family — a generator POP (chosen by pattern: 'noise' scatters count points and displaces them with a Noise POP for a moving cloud, 'grid' a flat lattice, 'sphere' a shell), a Transform POP that spins the whole field over time, then a render path (POP to SOP → Geometry COMP → Render TOP) output as a Null TOP. Creates a new baseCOMP under parent_path holding all of these and exposes PointSize and Spin knobs. NOTE: POPs are flagged Experimental in this TD build and the POP render path is uncertain, so this tool is built fail-forward and probe-first — the POP chain and render wiring are best-effort (failures become warnings) while the output Null is always created, and the result's extra.unverified lists every POP op type and the render path attempted so you can live-validate. Returns a summary plus a JSON block with the container path, created node paths, generator/transform/render/output paths, exposed controls, node errors, warnings, the unverified probe record, and an inline preview image.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoName for the self-contained POP-field container created under parent_path.pop_field
parent_pathNoParent COMP path the POP-field container is created inside (default '/project1')./project1
countNoApproximate point count. Used directly for the 'noise' pattern; 'grid'/'sphere' approximate it via a rows×cols layout near this total.
patternNoPoint layout/source. 'noise' (default) = a Point Generator POP scatters `count` points which a Noise POP displaces into a moving cloud. 'grid' = a flat Grid POP lattice. 'sphere' = points on a Sphere POP shell.noise
point_sizeNoRendered point size (Render TOP point size), exposed as the live PointSize knob.
spinNoDegrees/sec rotation of the whole field around Y (a Transform POP animates it over time), exposed as the live Spin knob.
resolutionNoRender resolution [width, height] of the Render TOP and the output Null TOP.
Behavior5/5

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

The description goes far beyond annotations, detailing the creation of a baseCOMP, exposed knobs, experimental status, fail-forward behavior, best-effort POP chain, and the always-created Null TOP. It also describes the return value including node paths, errors, warnings, and unverified probe record.

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 long but well-structured: purpose first, then step-by-step chain, notes, return details. While slightly verbose, every sentence adds value for such a complex tool. It is front-loaded and effectively organized.

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 no output schema, the description fully explains return values (summary plus JSON block with paths, control info, errors, warnings, probe record, preview image). It covers creation behavior, failure handling, and experimental notes, but could mention whether overwriting occurs or if parent_path must exist.

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 has 100% coverage, so baseline is 3. The description adds meaning beyond schema by explaining how 'pattern' affects the internal chain (e.g., noise scatters and displaces) and that point_size and spin are exposed as live knobs, providing context for parameter interactions.

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 it builds a GPU point field using TouchDesigner's POP family, with specific generator patterns (noise, grid, sphere). It distinguishes from siblings like create_gpu_particle_field and create_point_cloud by emphasizing the POP chain and experimental nature.

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

Usage Guidelines2/5

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

There is no explicit guidance on when to use this tool versus alternatives such as create_gpu_particle_field or create_point_cloud. While it notes experimental status and fail-forward behavior, it does not contrast with sibling tools or specify prerequisites.

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