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

Annotations only indicate readOnlyHint and destructiveHint, but the description adds substantial behavioral detail: experimental beta status, suppression below 5 transactions, county-level coverage, and the critical caveat that absence of a mapped zone is not asserted as 'safe'. These go well beyond the annotations and are essential for correct use.

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 description is long but well-structured, starting with the beta warning, then the core purpose, severity bands, addressing, aggregation, suppression, coverage, and final usage guidance. It is front-loaded with the most critical info and each sentence carries purpose, though it could be slightly more compact without losing essential details.

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?

Given the tool's complexity (severity bands, addressing nuances, suppression), the description covers the essential information. It explains severity bands with return periods, aggregation over all history, suppression threshold, and coverage. It does not explicitly describe the output format, but the purpose statement implies a report with severity breakdown, and there is no output schema to require it. Overall, it is sufficiently complete.

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% with detailed parameter descriptions, so baseline is 3. The description adds extra nuance: district codes resolve to the county, teryt wins when both are provided, and location inputs like a town within a powiat may 404, suggesting to check the catalog or use teryt first. This adds meaningful guidance beyond the schema.

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 description explicitly states the tool reports the share of a Polish county's real-estate transactions in flood-hazard zones, broken down by severity, from the RCN registry. It uses a specific verb ('report') and resource ('share of transactions in flood-hazard zone'), and clearly differentiates from siblings by mentioning the RCN registry and severity breakdown.

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 description gives explicit guidance on when to use the tool and when to use alternatives: it instructs to call list_flood_risk_locations first unless the location is a known major city, or to pass a 4-digit TERYT. It also explains the addressing rules (location vs teryt, teryt wins) and notes experimental beta status, advising not to build critical workflows.

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