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

With no annotations to lean on, the description carries the full burden and does so well: it discloses substring-only matching, the absence of fuzzy matching (with a concrete failure example), that single-character words are ignored, that an unlisted state code returns 404, the ordering rule, and that a miss yields an empty results list. That is exactly the behavioral detail an agent needs before calling.

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 matching semantics are front-loaded in the first sentence and the paragraphs are tight and purposeful. The reference to FEMA IDs is mildly gratuitous given no output schema is published, but the statutory context paragraph genuinely explains why the list exists.

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 tool with no annotations and no output schema, the description covers the return shape (results plus a total count), pagination defaults and ceilings, ordering, empty-result behavior, and the as_of snapshot date. Nothing an agent needs to invoke 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%, so the baseline would be 3, but the description genuinely adds meaning beyond the schema: it explains how multiple q words combine, shows worked examples, specifies limit's 50 default and 200 cap alongside offset, and documents the 404 outcome for an invalid state code.

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 line names a specific verb and resource ("Search FEMA-listed properties by name and town"), and the matching rules that follow make the name-plus-city scope unambiguous. It is implicitly distinct from siblings such as get_fema_hotel_by_id or get_fema_hotels_by_zipcode, but it never explicitly names those alternatives, so sibling differentiation is left to inference.

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 second paragraph supplies real decision context: federal travelers need a listed property to be reimbursed, and the tool returns no rates so it should be combined with the GSA per diem lookups. What is missing is explicit routing between this free-text search and the state/city or zipcode lookup siblings — an agent must infer when to prefer each.

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