Enhance a TouchDesigner build (LLM-planned)

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description adds crucial behavior: autoApply mutates the project, is not idempotent, and effects stack. This gives the agent clear understanding of side effects.

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 extremely concise at just two sentences. It front-loads the core action and then provides essential details about mutation and allowlist. No unnecessary words.

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 complexity (6 params, compound behavior, output schema), the description covers all needed information: what it does, when to use alternatives, behavior of autoApply, return value (before/after scores and dispatch log). Output schema existence further reduces need for return value details.

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%, so the schema already documents each parameter. The description adds minimal extra semantics beyond clarifying the purpose of focusCriterion and the meaning of autoApply and rescore. 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 clearly states the tool runs score_build, asks an LLM for allowlisted tool calls to improve weak sub-scores, and optionally auto-applies them. It distinguishes from siblings by being a compound tool that orchestrates other tools.

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?

Explicitly states when autoApply should be used (preview vs mutate), warns that it is not idempotent and re-runs stack effects. Also notes that focusCriterion excludes errors/perf, directing the agent to use summarize_td_errors or optimize_performance instead.

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