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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: 10-credit cost, UK-only scope, the widening radius/time algorithm until at least 6 qualify, the never-drop-but-flag behavior, the current-record caveat with attributes_after_sale, and the instruction to time-adjust prices with the index.

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?

Dense but front-loaded, leading with the core purpose and scope before the qualifying rules and return fields. It is a long single block, but almost every sentence adds decision-relevant information, so there is little waste.

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?

For a complex valuation tool with an output schema, the description is complete: it covers scoping rules, cost, geography, keying, and the semantics of returned flags and scores. An agent has everything needed to invoke it correctly and interpret the results.

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 0%, so the description must compensate and does: as_of accepts YYYY-MM or YYYY-MM-DD with default today, limit is 1-60, and uprn is a UPRN key with guidance on how to obtain it rather than passing an address.

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 verb and resource: 'Comparable completed sales for a valuation, beyond the property's own building.' The scope word 'beyond the property's own building' distinguishes it from sibling tools like property_comps and transactions_by_uprn that surface the subject's own sale.

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 explicit workflow guidance — it is keyed on a UPRN, not an address, and tells the agent to call address_autocomplete (free) to narrow, then address_resolve to get one. It also states the qualifying criteria and the 'review contrary sales rather than ignoring them' stance, so the agent knows exactly when and how to use it.

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