Create NPR painterly filter

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

Annotations are readOnlyHint=false, destructiveHint=false, openWorldHint=true. The description adds behavioral context: it creates a specific node chain (Select TOP → GLSL TOP → Null TOP), exposes parent parameters, and notes that glsl_compile_verified is always false offline, requiring post-cook verification with get_td_node_errors. No contradiction with annotations.

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 is detailed yet concise, front-loaded with the purpose, followed by algorithmic details, node chain construction, and return values. Every sentence provides necessary information without redundancy.

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 (9 parameters, no output schema), the description covers the creation process, return values, and verification steps. It explains the required source_path and modes but could elaborate on return format details. Overall, it is sufficiently complete for agent use.

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?

Schema description coverage is 100%, and the description adds value by explaining the Kuwahara algorithm, mode differences, cost implications (O(radius²·sectors)), and live control exposure. While the schema already documents parameters, the description deepens understanding moderately.

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 clearly states 'Apply a non-photorealistic painterly filter to an existing TOP.' It specifies the verb (apply), resource (painterly filter), and target (existing TOP), and distinguishes itself from sibling tools like create_glsl_shader by focusing on the NPR filter node chain.

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 explains when to use the tool (for applying a painterly filter) and lists different modes, but does not explicitly state when not to use it or mention alternative tools. Given the extensive sibling list, more guidance on prerequisites or comparisons would improve the score.

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