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

With no annotations, the description carries the full burden and does so: it discloses matching semantics (word-contains for areas, exact case-insensitive for counties/cities, optional trailing 'county'), the RUS fallback, that multiple areas can be returned for one name and that the duty station disambiguates, and that territories are excluded.

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?

Purpose and the code-return value are front-loaded and nearly every sentence carries operational detail. There is mild redundancy ('keeps the areas whose name contains every word' is restated later as 'Area names keep matching on any word they contain'), and the trailing caveats could be tightened.

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, yet the description explains the result shape (`matched_places` listing the counties and cities behind each result) and covers the tricky failure modes (multiple matches, RUS, misspellings, uncovered territories). An agent has everything needed to call and interpret it.

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 baseline is 3, but the description goes well beyond the terse schema text: it defines how `location` matches area names versus county/city names, the optional 'county' suffix, case-insensitivity, and the non-obvious rule that `state` only narrows `location` and is inert without it.

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 ('List the locality pay areas of the latest pay year') plus the return payload ('the code to use on the pay endpoints'), and the opening line adds the optional county/city scoping. It also distinguishes itself from the county-lookup sibling by directing payroll use to '/v1/opm/localities/county/{fips}'.

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 when-to-use (resolve a GS locality code for pay endpoints), when-to-use-something-else (payroll should use the county endpoint because OPM does not publish city data), and an explicit exclusion caveat (empty result does not mean RUS; territories are not covered). The dependency rule 'state has no effect without location' is stated outright.

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