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

With no annotations, the description carries the full burden; it does disclose a meaningful behavior — missing hazard evidence remains 'unavailable' rather than being fabricated, and downstream inferences are suppressed. It never states read-only semantics, what a returned suggestion contains, or any permissions/rate behavior, so coverage is partial.

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 short sentences with no filler, and the scope statement leads. But two of the three sentences are negative disclaimers and the key noun phrase 'retained property observations' is left undefined, so the structure informs less than its length permits.

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 and no annotations, so the description must explain the return shape and safety profile; it establishes the boundaries of inference well but never says whether this is a read operation or what a suggested check looks like. Adequate to prevent misuse, not adequate to call it confidently.

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 description coverage is 100%, so address_or_pidn and county_key are already documented (including the county-scoping and conflicting-prefix rejection behavior). The description adds no additional parameter meaning, so the baseline 3 applies.

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 verb (suggest) and resource (evidence checks derived from retained property observations) are stated, but 'evidence checks' and 'retained property observations' are never grounded, so the agent must guess what artifact comes back. The disclaimers imply it is not an assessment or audit tool, which edges it away from siblings like audit_fema_flood_hazard, but the core purpose stays abstract.

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?

Negative guidance is explicit and useful: county weather events do not establish parcel damage, and no defect, repair cost, deduction or filing readiness is inferred — this tells the agent not to route storm/flood audit questions here. However, there is no positive statement of when to call it instead of get_condition_evidence_catalog or audit_parcel_blight_citations.

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