Skip to main content
Glama

Create particle flock

create_particle_flock

Simulate a boids-style GPU particle flock with separation, alignment, and cohesion. Creates a TouchDesigner network with instanced dots, camera, live controls, and returns node paths and preview.

Instructions

Build a boids-style GPU particle flock: position and velocity are simulated entirely on the GPU in two RGBA32float feedback-TOP loops, where the velocity shader implements the three classic boids rules — separation, alignment, cohesion — by scanning a stencil of neighbouring texels in the agent texture (each texel is one agent), then renormalising toward a cruise speed. Positions drive TOP-instancing of a tiny dot once per agent. Creates a new baseCOMP under parent_path holding the velocity/position feedback loops, the instanced Geometry COMP, Camera, Light, and Render TOP ending in a Null output. The behavioural complement to create_gpu_particle_field (use that instead for curl-noise/gravity drift rather than flocking); also pick a sibling for other motion: image_to_particles to spring particles onto the pixels of an image/video, create_pop_particle_system for TouchDesigner's native POP particle network, create_particle_system for a simple CPU emitter. Exposes live Separation / Alignment / Cohesion / Speed knobs. Note: the flock only evolves while the TD timeline plays. Returns a summary plus a JSON block with the container path, created node paths, the agent count, the output path, exposed controls, any node errors, warnings, and an inline preview image.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
colorNoRGB colour (0..1) of the instanced dots — the colour of the school.
countNoEdge of the square agent buffer; the flock is count×count agents (agents = count², e.g. 64 → 4096). Each agent is one texel of the RGBA32float position/velocity buffers. Capped at 256 (65 536 agents) because the per-agent neighbour scan cost grows with the texture.
speedNoCruise speed the velocity is renormalised toward each frame, so the school flies at a stable pace.
cohesionNoBoids cohesion weight: steer toward the centroid (average position) of neighbours.
alignmentNoBoids alignment weight: steer toward the average heading of nearby neighbours.
point_sizeNoRadius of each instanced dot (the sphere SOP scale).
separationNoBoids separation weight: steer away from close neighbours (collision avoidance).
parent_pathNoParent network where the flock container is created (default '/project1')./project1
expose_controlsNoWhen true (default), expose live Separation / Alignment / Cohesion / Speed knobs on the system container.
Behavior5/5

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

Despite annotations being minimal, the description reveals extensive behavioral detail: it creates a baseCOMP under parent_path with specific components, uses GPU feedback loops, exposes live knobs, and returns a detailed JSON with node paths and errors. There is no contradiction with readOnlyHint=false, openWorldHint=true, or destructiveHint=false; the creation is consistent with these hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence delivers value: it front-loads the main purpose, describes the internal GPU mechanism, gives sibling comparisons, states the timeline requirement, and enumerates the return payload. The structure is logical and repetitive content is absent, making it appropriately concise for the tool's complexity.

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

Completeness5/5

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

Given the tool's complexity (GPU simulation, multiple components) and absence of an output schema, the description covers all necessary context: what is built, how it works, when to use it, runtime caveats, and exactly what the response contains. This allows an agent to invoke the tool correctly without additional information.

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 the baseline is 3. The description adds no significant parameter-level semantics beyond what the schema already provides; it only references exposed controls (Separation, Alignment, Cohesion, Speed), echoing the expose_controls parameter. Thus it stays at baseline.

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 opens with a specific verb and resource: 'Build a boids-style GPU particle flock', clearly defining the tool's core function. It also distinguishes from siblings by naming create_gpu_particle_field, image_to_particles, create_pop_particle_system, and create_particle_system, so an agent can easily tell this tool apart.

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 explicitly provides usage guidance: it names alternatives and when to prefer them (e.g., 'use create_gpu_particle_field for curl-noise/gravity drift rather than flocking'). It also adds a critical runtime condition: the flock only evolves while the TD timeline plays, which is essential for correct use.

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/lucasmaher-hash/touch-designer-mcp'

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