Enhance a TouchDesigner build (LLM-planned)

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

The description significantly enriches the annotations by disclosing critical behavioral traits: preview-only defaults, autoApply never bypassing approval, CAS/readback, and compensating restore. It also clarifies that legacy calls are unchanged. This goes far beyond the sparse annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) and provides valuable safety and execution 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 is compact—three sentences—and front-loads the core purpose. Each sentence adds value, though the third sentence is dense with specialized terminology (e.g., 'calibrated local vision receipt', 'CAS/readback') that may reduce accessibility. It is efficient but not maximally clear.

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 (7 parameters, nested objects, output schema), the description sufficiently covers the high-level workflow, including the role of score_build, the bounded nature of improvements, and critical safety mechanisms. The schema handles parameter details and return values, so the description does not need to repeat them. It provides enough context for correct selection and 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?

The input schema provides 100% coverage with descriptions for all parameters, including detailed explanations for visualCritique, autoApply, and focusCriterion. The tool description itself adds no parameter-specific meaning beyond the schema, so it meets the baseline but does not exceed it.

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 the tool's function: it runs score_build and uses an LLM to create bounded allowlisted improvements. It differentiates itself from siblings like score_build (which only scores) and optimize_performance by focusing on LLM-driven enhancement with preview and approval. The clause 'Legacy calls are unchanged' further clarifies its scope.

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 usage after score_build and mentions safety defaults, but it does not explicitly state when to use this tool versus alternatives like optimize_performance or summarize_td_errors. It relies on the schema's focusCriterion parameter for exclusions, which is not part of the description. Thus, usage context is present but not fully explicit.

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