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

Annotations only declare readOnlyHint and openWorldHint=false; the description adds real behavioral context beyond them: ghost-town rows live in a separate Wikidata corpus invisible to point/name searches, and such queries are refused rather than returned empty. It also discloses result provenance (byway.world page link, OpenStreetMap/Wikidata traceability), none of which the annotations carry.

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-loaded with the verb and resource, then the locator modes, then the corpus caveat; every sentence carries information. It is dense and slightly performative in phrasing ('One limit, stated:'), but the length is justified by the genuinely non-obvious corpus constraint.

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 usefully covers return content (result links to byway.world, provenance records). Remaining gaps are minor: the default and ceiling for limit, and how locator combinations other than name+locator interact, are left to the schema or unstated.

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 86%, so the schema already documents most parameters and the baseline is 3. The description adds meaning the schema does not: that a name acts as a narrowing filter when combined with a locator, and that the corpus split makes point/name searches blind to ghost towns, which constrains how lat/lon/name may be combined.

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 ('Search the Byway atlas of typed places') and enumerates the kinds it covers, so the agent knows exactly what domain is searched. It is clearly distinguished from siblings like get_place, search_byways, and search_lookouts, which cover single places, routes, and lookouts respectively.

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 lays out three locator modes (state+kind, point+radius, name) and states that a name alongside a locator narrows results. It names the alternative (get_place) for the one case this tool cannot serve and states the failure mode ('refused, never answered empty'), which is exactly the when/when-not guidance an agent needs.

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