Create flow abstraction

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

Annotations only say readOnlyHint is false and destructiveHint is false; the description adds useful behavioral detail: it creates two glslTOPs plus textDATs, uses a Select TOP and ends with a Null TOP, and explains that some parameters are live uniforms while others are baked. It also clarifies that Iterations does not create a ping-pong feedback loop, adding genuine beyond-annotation context.

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?

The description uses four dense sentences, each covering a distinct aspect: algorithm, output structure, parameter lifecycle, and iteration semantics. It is front-loaded with the core purpose and contains no filler. It is appropriately sized for the complexity, though slightly information-dense.

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?

Given the tool's complexity (11 params, no output schema), the description is remarkably complete: it explains the algorithm, the nodes created, the wiring via Select/Null TOPs, which parameters are live vs baked, and the in-shader iteration behavior. Together with the rich schema, this gives an agent everything needed to invoke it correctly.

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 documents all 11 parameters (100% coverage), so the baseline is 3. The description goes further by explaining that Strength/Edge/Iterations are live parent-par-bound uniforms, while blur radius, sigmas, and tau are baked at build time, and that Iterations boosts ETF strength in-shader. This adds behavioral meaning beyond the individual field descriptions.

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 starts with a specific verb and resource: 'Build a two-pass Kyprianidis-style flow abstraction.' It names the exact pipeline stages (ETF bilateral smoother + FDoG line extractor) and the created objects (two glslTOPs + companion textDATs), distinguishing it clearly from generic 'create_npr_filter' or post-processing siblings.

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?

The description implies the use case via the visual result ('oil-painting smooth interiors with crisp coherent ink edges') and explains build-time vs live parameters, but it does not explicitly state when to prefer this tool over alternatives like create_npr_filter or create_optical_flow. It gives clear context but no explicit exclusions or alternative naming.

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