Score a TouchDesigner build

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

Adds meaningful context beyond annotations: describes read-only nature, optional LLM critique with failure-safe behavior, and that it composes existing endpoints. Annotations already provide safety profile, so the description complements without redundancy.

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?

Two sentences, front-loaded with core purpose, no filler. Each sentence adds value: purpose, return values, optional feature, and behavioral note.

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?

Covers key aspects: read-only, scoring rubric, return sub-scores and suggestions, optional critique. With output schema present, return values need not be detailed. Minor gap: doesn't explain that scoring requires a built network, but this is implicit from 'score a built network'.

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% description coverage, so baseline is 3. The description only mentions 'llmCritique' parameter in context; no additional semantic enrichment for other parameters like scopePath or criteria.

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?

Clearly states the tool scores a built network 0-100 on a fixed rubric, returning per-criterion sub-scores and improvement suggestions. Distinguishes from siblings by specifying read-only and composition of existing endpoints, avoiding confusion with creation tools like 'create_*' or analysis tools like 'analyze_project'.

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?

Implies usage for scoring a built network with optional LLM critique, but does not explicitly state when to use this tool over alternatives or provide exclusions. The description lacks guidance on prerequisites or comparison to similar tools.

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