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

With no annotations, the description carries the full behavioral burden and does so thoroughly: result ordering (city then name), pagination semantics with default 50 / max 200, the meaning of `total`, 404 on unsupported state codes, empty results for non-matching cities, and that FEMA publishes only the current list with an `as_of` snapshot date. It also discloses a key negative trait — no rates returned.

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 core operation, then pagination, then matching rules, then domain context. Four paragraphs are slightly more than strictly needed — the Fire Safety Act background is useful motivation but could be tightened — though nothing is redundant filler.

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?

No output schema exists, and the description compensates by naming the returned fields it references (`results`, `total`, `as_of`) and their meaning. Together with the 404 and empty-list behavior, an agent has everything needed to call and interpret the response.

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 value: the enumerated set of accepted state codes (50 states, DC, AS/GU/MP/PR/PW/VI), the 404 consequence for others, and a concrete partial-matching example ('york' matches New York and Yorktown). It restates limit defaults from the schema, keeping it just under a 5.

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?

Opens with a specific verb+resource+filter: FEMA-listed properties by state, optionally filtered by city. It is clearly distinguishable from siblings like get_fema_hotels_by_zipcode, get_fema_hotel_by_id and search_fema_hotels by its geographic key.

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?

States the context in which the tool is appropriate (federal traveler lodging reimbursement under the Hotel and Motel Fire Safety Act) and points to GSA per diem lookups for rates since this endpoint returns none. It never explicitly names a sibling as the alternative for other access patterns (e.g. zip code), so the routing guidance is a 4 rather than a 5.

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