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

Annotations already declare it a safe read-only, idempotent operation, and the description goes well beyond that: it discloses that only latest report versions come back with CSV citations and no narrative text, that no report has its own NHTSA web page, that caveats are returned verbatim, that counts are not rates or rankings, and that the June 16, 2025 amended order breaks comparability.

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 purpose is front-loaded, but the body is a dense wall of caveats with visible redundancy — 'say nothing about responsibility' and 'the highest injury severity alleged says nothing about responsibility' cover the same ground, and the non-comparability point is echoed in two places. Several sentences could be merged without losing information.

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 no output schema, the description carries the burden for return values and does so: latest versions, CSV citations, no narrative, no people, verbatim NHTSA caveats. Combined with full schema coverage and read-only annotations, an agent has enough to call and interpret this correctly.

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 every parameter is already documented, including the ADS/ADAS separation and the 'alleged severity, not responsibility' caveat for severity. The description mostly restates those constraints rather than adding new syntax or semantics, so the baseline 3 applies.

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?

Opens with a specific verb and resource: 'Search NHTSA Standing General Order crash-report rows in the MORVS Self-Driving Crash Register.' It also sharply delimits scope ('OTHER filings are never returned as crashes'), which separates it from sibling tools like self_driving_company or nhtsa_recent.

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?

States the hard precondition (requires ADS or Level 2 ADAS) and enumerates the available filter dimensions, so an agent knows when this tool is the right one. It never names an alternative tool or an explicit 'do not use this for X, use Y' condition, which keeps it from a 5.

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