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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real value: it discloses the return columns (crashes, fatalities, persons/vehicles/pedestrians), the error contract ('unknown states are refused with a clear error, never an empty success'), and a coverage caveat. Only minor gap is no note on result size or ordering.

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?

Front-loads what the tool returns, then parameters, then coverage limits, then error behavior — four tight sentences with no filler. Every sentence carries information an agent needs.

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?

No output schema exists, and the description compensates by enumerating the returned fields plus the error and coverage semantics for this two-parameter tool. Nothing an agent needs to call it correctly is 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 description coverage is 100%, so the accepted state formats (name/postal/FIPS) and optional-year semantics are already documented there. The description restates these without adding syntax or format detail beyond the schema, so 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?

States a specific verb and resource ('fatal motor-vehicle crash counts and fatalities for a US state'), names the authoritative source (NHTSA FARS), and scopes it to a state/year query. This clearly distinguishes it from siblings like fars_coverage or fars_vehicle_makes.

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?

Explains when to omit the year and explicitly redirects to fars_coverage 'for the exact range,' giving the agent a clear alternative for coverage questions. It doesn't spell out exclusion cases beyond coverage, so not a full 5.

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