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

Adds real context beyond annotations by disclosing the data source (the fixed ~800-code NEISS coding manual) and that no network call occurs, which tells the agent results are stable and cheap to repeat. However, "Entirely local ... no live call" sits at odds with the openWorldHint=true annotation, a mild inconsistency an agent may notice.

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?

A single front-loaded sentence with purpose, examples, downstream routing, and data provenance — no filler. The em-dash clause is doing genuine work rather than restating the tool name.

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?

With an output schema present, return shape need not be described, and the description covers source, locality, and intended next step. It leaves unstated how an agent should behave on empty or overly broad result sets, the one real gap for a lookup tool.

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 coverage is 100% and the schema already documents case-insensitive substring matching and the limit range, so the description need not explain parameters. The example keywords hint at useful query shapes but add no matching semantics beyond the schema.

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?

Specific verb+resource ("look up CPSC NEISS product/activity codes") plus concrete example keywords ("pool", "ATV", "trampoline"). It also distinguishes itself from the sibling family by naming the downstream consumer, neiss_injuries, and by describing the classification-browsing use case.

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 says when to reach for it: to resolve a product_code before calling neiss_injuries, or to inspect CPSC's categorization. It stops short of naming exclusions, e.g. that neiss_top_products should be used for ranked/aggregate views or what to do when zero matches come back.

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