Create dither

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses the full side-effect profile: it creates a new baseCOMP containing a source, GLSL TOP with inline shader, and Null output; exposes live knobs; returns summary/paths/controls/preview; and explains the optional self-contained noise source with no device permissions. This exceeds the baseline for mutation tools.

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

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

Four dense sentences, each carrying essential information: effect type, palette modes, node structure, dynamic controls, and return payload. No redundant phrasing or filler; front-loaded with the core purpose.

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

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

For a complex 12-parameter creation tool with no output schema, the description effectively covers what gets created, how it behaves, and what is returned. It also notes the self-contained noise source fallback. This gives an agent a complete mental model for invocation.

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

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

Input schema has 100% coverage with detailed descriptions for all 12 parameters, so the description need not restate them. It adds high-level context (e.g., '2/4/16-colour palette' maps to bits, 'Mix, Threshold, and Scale knobs' map to parameters) without introducing new meaning per parameter. Baseline 3 is appropriate.

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

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

The description opens with 'Build a retro dither effect' using a specific verb and resource, enumerates supported patterns (Bayer, checker, noise, error-diffusion) and palette modes, and lists concrete node outputs. This clearly distinguishes it from visual-effect siblings like create_halftone or create_glitch.

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

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

Provides clear context that this tool is for creating a dither effect and describes the resulting node structure and interactive knobs, implying when to use it. However, it does not explicitly name alternatives or exclusions, though the specificity of 'retro dither effect' is enough to differentiate from sibling creation tools.

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