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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered and the description wisely spends its words elsewhere. It adds genuinely non-inferable behavior: results are sorted largest first, only cities with 5+ monitored properties are covered, and each record carries a page URL and HUD project id. Gaps: 'largest first' never says largest by what measure, and pagination/truncation behavior past the limit is unstated.

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 tight sentences with no filler, and the resource plus scope lead the first sentence. The 5-property coverage caveat is appended as a trailing clause where it is easy to skim past, when a coverage warning arguably deserves its own sentence.

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, so the description carries the return-value burden and does partly meet it by naming the URL and HUD project id each result carries. Combined with the coverage threshold and ordering, an agent knows enough to call this correctly. What is missing is the rest of the result shape plus behavior at the limit boundary (default 10, max 50).

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 75%, so baseline is 3. The description restates the state/city/name scoping already documented in the schema and adds only a hint about fuzzy name/street matching ('name or street fragment'), which goes slightly beyond 'Words from the property name or street address'. The limit parameter and its 1-50 range are never mentioned, and 'largest first' is not tied to limit or sort semantics.

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 (HUD-listed LIHTC properties still monitored for compliance) plus the exact scope of filtering (one state, optional city and name/street fragment) and ordering. That is well beyond a restated name. It stops short of distinguishing itself from the sibling get_state_lihtc, whose name suggests an overlapping state-scoped listing, so the agent must infer which one to reach for.

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?

Gives clear context for use: one required state, optional city/name narrowing, largest-first ordering, and a chaining instruction that result ids feed get_property. The 'cities with 5 or more monitored properties' caveat acts as a partial exclusion, warning that small-city queries will come back empty. No explicit statement of when to prefer get_state_lihtc or how it differs from a city-level lookup.

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