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

Annotations cover safety (readOnly, idempotent, non-destructive, open-world), and the description adds substantial context beyond them: 30-day caching, Census geocoding with the returned point, ambiguous addresses refused with candidates, unmapped vs. low-risk distinction, outside-US not-found-and-not-charged handling, higher-risk zone on boundaries, 2c billing, and the mandatory disclaimer.

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 lede sentence is well front-loaded and answers the question immediately, but the body is long and repeats itself — 'Live from FEMA's National Flood Hazard Layer' and 'whether it is in the Special Flood Hazard Area' each appear twice, and the second paragraph re-lists fields already given in the first.

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?

An output schema exists, so return values need not be explained, yet the description still covers the operational facts an agent needs: cost, caching, disclaimer obligations, geocoding path, and every edge case (unmapped, unmapped-but-not-low-risk, outside US, boundary ties). Nothing material is missing for a 3-param, no-required-param tool.

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 the baseline is 3, but the description adds real meaning beyond the schema: the address is geocoded with the Census Bureau geocoder, the resolved point is returned, and an ambiguous address is refused with its candidates rather than silently resolved. It confirms address and lat/lon are alternatives but does not spell out what happens if both or neither are supplied.

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 resource (FEMA flood zone for a US address or coordinate) and enumerates exactly what is returned: zone, SFHA membership, base flood elevation with datum, FIRM panel and date, NFIP community, LOMR. It also names the sibling it is not (address_profile), so an agent can route without opening 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?

Has an explicit 'When to use' block covering the triggering questions (in a flood zone, needs flood insurance, in the SFHA or floodway) and names the alternative tool address_profile plus the condition for choosing it. The 'not an official determination / not an elevation certificate' exclusion is stated too.

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