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

Annotations only cover the read-only/safe profile, but the description adds substantial extra context: an EXPERIMENTAL/beta stability warning, all-time aggregation with no date window, suppression below 5 assessed transactions, and the important caveat that absence of a mapped zone is not asserted as 'safe'. These are real behavioral traits not derivable from the structured fields.

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 beta notice is front-loaded appropriately, and severity-band calibration and suppression rules are each stated once and compactly. It is on the longer side, with the teryt-precedence rule appearing in both description and schema, but every sentence carries distinct information.

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?

With no output schema, the description carries the burden of return semantics and does so well: it defines the severity bands via return periods, the assessed-transaction threshold, the county-level granularity, and the all-time window. The exact output shape (shares vs counts, field names) is only implied, which is the remaining gap.

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% and the parameter descriptions already state the truncation, district, gmina-candidate and 'teryt wins' rules, so the description largely restates them. It does tie the parameters to a routing decision (when to prefer the catalog lookup), but adds little syntax or format detail beyond the schema, so the baseline of 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?

Opens with a concrete verb+resource+scope: the share of a Polish county's real-estate transactions falling in a mapped flood-hazard zone, broken down by severity, sourced from the RCN registry. This is clearly distinguishable from sibling assets like get_transaction_flood (transaction-level) and list_flood_risk_locations (catalog). An agent can select it without opening another 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?

Gives an explicit prerequisite workflow: call list_flood_risk_locations FIRST unless the location is a known-covered major city, or pass a 4-digit county TERYT. It also spells out the alternatives (location vs teryt), the precedence rule, and the dry-run case for ambiguous gmina names, leaving nothing to inference.

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