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

With no annotations, the description carries full burden, and it usefully discloses that results carry 'official sources and a last-checked date' — behavior an agent could not get from the schema. It still omits result ordering, whether curated content can go stale, and any rate or scope limits.

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?

Three sentences, each earning its place: scope first, output guarantee second, and concrete query examples last for pattern-matching. Zero filler and properly front-loaded.

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?

For a 4-parameter read-only search with no output schema and no annotations, the description covers purpose, coverage breadth, and result provenance (official sources, last-checked date). Minor gaps: no guidance on the limit cap or on empty-result behavior.

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?

The description adds nothing about the four parameters — no mention of island, type, or limit usage, and no guidance on writing effective queries is needed since the schema already says 'in plain words.' At 75% schema description coverage the schema does the heavy lifting, so baseline 3 is appropriate.

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?

A well-defined verb-plus-resource scope: 'Search verified Hawaiʻi visitor and resident facts,' with concrete domains (beaches, ocean safety, wildlife rules, sunscreen laws, lodging taxes) that differentiate it from the narrow getters in its sibling set. However, it never explicitly disambiguates against get_hawaii_weather or get_hawaii_alerts, which overlap its 'ocean safety'/'safety' coverage.

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 two example questions ('Do I need a reservation for Hanauma Bay?' / 'How close can I get to a sea turtle?') make the retrieval context concrete and easy to match. There are no exclusions or explicit alternatives ('for current conditions, use get_hawaii_weather'), so the conditional routing is left to inference.

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