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

Goes well beyond the readOnly/idempotent annotations: it discloses that the returned figure is a CPSC statistical weight sum, not a raw case count, that the underlying sample size is returned alongside, that estimates under ~20 sampled cases are flagged unstable and shouldn't be quoted precisely, and the coverage boundary (ED-treated only, no deaths or other hospitalizations). These are exactly the caveats an agent needs to report the number responsibly.

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 core definition and the 'how many people were injured by X' framing are front-loaded, and every sentence carries substantive information. It is a dense single paragraph, though, mixing methodology, input routing, and coverage caveats without visual separation.

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 and rich annotations, the description supplies the remaining domain context — weighting methodology, sample-size instability threshold, and scope exclusions — that structured fields cannot express. Nothing essential for correct invocation or interpretation appears missing.

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%, so the baseline is 3; the description adds meaningful routing context by framing product_code and product as alternative resolution paths and pointing to neiss_product_codes for codes, plus noting age_range is optional narrowing. It does not add syntax or format detail beyond the schema for year/from_year/to_year ranges.

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?

States a specific resource and verb-like operation: a national WEIGHTED estimate of consumer-product ED injuries from CPSC's NEISS system, with concrete example questions it answers. It is clearly distinguishable from the sibling neiss_product_codes (code lookup) and neiss_top_products (rankings), and it explicitly names the code-lookup sibling as the place to find product codes.

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?

Gives explicit input paths (exact 4-digit product_code OR free-text product name) and notes that ambiguous names return candidates rather than a number, which routes the agent toward the code lookup when precision matters. Also states the optional age_range narrowing. It stops short of stating when NOT to use this tool versus neiss_top_products for ranked 'top product' questions.

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