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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantially more: a fixed corpus of 49 beaches, a hard 'returns up to 5' cap, data freshness via a last-read date, and explicit failure behavior (`townScope.recognized: false` yields empty rows plus `didYouMean`). It also discloses that the dog rule is month-based and split morning/daytime, so an agent knows the answer is date-sensitive rather than static.

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 scope are front-loaded and every clause carries information — return cap, field list, permit boundary, failure mode. It is a single dense paragraph, though, and the parenthetical detail about South Fork off-leash dawn rules is more color than routing signal; splitting the return-contract sentences out would improve scanability.

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?

There is no output schema, so the description must carry the return contract, and it does: it enumerates the returned attributes, states the 5-row cap, and explains the `readAs`/`townScope`/`didYouMean` envelopes including the empty-rows case. For a one-parameter lookup over a bounded dataset, nothing an agent needs in order to call it or interpret the response 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 coverage is 100% and the single parameter is already documented, so the baseline would be 3. The description earns more by explaining resolution semantics the schema does not: 'Amagansett, NY' and 'Sag Harbour' both resolve, `readAs` reports which place was answered, and near-miss names produce `didYouMean` — meaning an agent learns the argument is fuzzy-matched place text, not an exact key.

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?

The opening sentence names a specific resource and scope: one named beach, or every verified beach in a town/village/hamlet, and it lists the concrete fields returned (dog rule today, parking permit, car-free access, lifeguard hours, rip currents, governing source, last-read date). It also bounds the permit scope ('the line for each named beach only; it does not include non-resident day passes or the permit map by jurisdiction'), which separates it from the parking_permit_rules sibling without needing to open either schema.

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?

The description makes the selection condition explicit — pass a beach name, or a town/hamlet/village to get all verified beaches there — and states a clear exclusion for permit data that lives elsewhere (day passes, permit map by jurisdiction). It stops short of naming the sibling tool to use instead, so the routing is implied rather than spelled out.

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