Skip to main content
Glama

Create feedback tunnel

create_feedback_tunnel

Build a parametric infinite-zoom feedback tunnel in TouchDesigner with adjustable zoom, rotation, hue shift, and decay. Uses a source TOP or animated noise seed.

Instructions

Build a parameterized infinite-zoom/rotate feedback tunnel: a seed TOP is composited with its own fed-back, zoomed, rotated, and decayed frame each cook to produce a hypnotic inward-spiral tunnel. Four audio-bind-ready controls (Zoom, Rotate, HueShift, Decay) are exposed on the container for live performance. A built-in animated noise seed is used when no source TOP is given. The recipe-validated topology (noiseTOP → feedbackTOP + compositeTOP-maximum → transformTOP sx/sy → blurTOP → levelTOP brightness1/huerotate → nullTOP, loop closed by feedbackTOP.par.top) is created inside a new baseCOMP under parent_path. Returns a summary, the container + node paths, exposed controls, any node errors, and an inline preview image.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNofeedback_tunnel
parent_pathNoParent COMP path inside which the 'feedback_tunnel' container is created./project1
sourceNoPath to an existing TOP to use as the tunnel seed. Omit to generate a built-in animated noise seed.
zoomNoPer-frame zoom factor applied to the fed-back frame (>1 = inward tunnel, e.g. 1.02).
rotateNoPer-frame rotation in degrees added to the fed-back frame (positive = clockwise).
hue_shiftNoPer-frame hue rotation (0–1, wrapping). Applied via levelTOP huerotate. 0 = no shift.
decayNoTrail persistence (0–1). Applied via levelTOP brightness1 each frame. Higher = longer-lived tunnel; default 0.95.
resolutionNoOutput resolution [width, height] in pixels. Fixed resolution prevents feedback runaway.
Behavior4/5

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

Annotations already indicate non-destructive, non-readonly behavior. The description adds context about topology creation and node paths, but does not mention side effects like overwriting existing components.

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 informative paragraph that packs topology details, controls, and return info without unnecessary words. It could be slightly more structured but is efficient.

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?

Despite having no output schema, the description covers the topology, controls, and return values sufficiently for an agent to understand and invoke 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?

With 88% schema coverage, the description enhances parameter understanding by explaining effects (e.g., zoom factor >1 inward tunnel, decay for trail persistence) beyond the schema's basic descriptions.

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 parameterized infinite-zoom/rotate feedback tunnel with specific controls, distinguishing it from siblings like create_feedback_network or other generative art tools.

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 what the tool does but does not provide explicit guidance on when to use it versus alternatives like create_feedback_network or create_kaleidoscope. Usage must be inferred from the purpose.

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