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

Annotations declare readOnlyHint=false, idempotentHint=true, openWorldHint=true, destructiveHint=false, but the description adds crucial context the annotations cannot: the first lookup triggers background data gathering taking a minute or two, with status.gathering or status.researching_county_record flags, and must be polled via get_parcel rather than re-invoked. It also discloses the authentication requirement and that it returns a shareable page URL and live listings, none of which is in structured fields.

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?

The single sentence is dense and front-loads the core purpose, but the enumeration of data classes is long and the critical async/polling instruction is buried near the end. It is somewhat overstuffed with return-value detail for a tool without an output schema, reducing scannability.

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?

Given one parameter with full schema coverage, no output schema, and a moderately complex async behavior, the description is fairly complete: it covers what data is returned, the async polling flow, auth requirement, and the shareable URL. It does not detail error behavior (e.g., refused addresses, signed-out errors) or the exact response shape, but for this tool that gap is minor.

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 address parameter already carries a detailed description including a format example and validation rule (road/town/partial refused). The description adds nothing about the address parameter itself, so it is at the baseline for high coverage; no penalty but no credit either.

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 description states a specific verb (look up) and resource (US building by street address) and enumerates the data classes returned (FEMA flood zone, EPA records, Census demographics, county public record). It is distinguishable from the sibling get_parcel, which it references as the polling mechanism, but the split of responsibilities between look_up_parcel (initiate) and get_parcel (check progress) is only partially clarified.

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 gives clear usage context: works for any building regardless of listing status, requires a signed-in account, and explicitly instructs to use get_parcel with the returned hashid while status is gathering/researching instead of repeating the lookup. It does not explicitly say when NOT to use it versus geocode_address or search_listings, but the primary when-to-use and the polling alternative are well covered.

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