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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description adds value they cannot express: per-item outcomes (ok | not_found | error) returned in input order, partial-failure semantics, and billing that is per property answered and never exceeds the sum. Pricing (5 credits / 5p), regional limitation, and the UPRN keying constraint are all disclosed up front.

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?

Four dense clauses, each carrying distinct information: identity, return shape, billing, geography/keying. Nothing is repeated from the title or schema, and the most decision-relevant facts (batching, UPRN keying) come first.

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 an output schema present, return-value explanation is rightly omitted, and the description covers the remaining risks an agent faces: wrong key type, wrong country, cost, and partial failure. Edge cases such as duplicate UPRNs or behavior above the 100-item cap are not addressed, which keeps it short of 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 0% for the single `uprns` parameter, so the description must carry the burden — and it does: it identifies the parameter as UPRNs (not addresses) and bounds the array at 100 items. It does not spell out the UPRN form (integer identifier) or duplicate handling, leaving a small residual gap.

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 by naming the sibling it batches (`property_risk_report`) and states the scaling factor (up to 100 properties in one call). The verb/resource relationship is unambiguous, and an agent can immediately tell it apart from the single-property tool, address tools, and unrelated reports.

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?

Explicitly restricts scope ("UK only"), states the keying requirement ("Keyed on a UPRN, not an address") and prescribes the prerequisite chain: `address_autocomplete` (free) to narrow, then `address_resolve`. It stops short of saying when to prefer the single-property `property_risk_report` over the batch, but the "up to 100 in one call" framing makes that inference nearly trivial.

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