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

Annotations already declare the safe-read profile (readOnlyHint, idempotent, non-destructive), so the bar is lower. The description nonetheless adds meaningful edge-case behavior: the factor and anchored value are null when no series can carry the sale, the anchor is diagnostic and never carried at 1.0, and an empty anchor is returned when no registered sale is linked. It also states scope (UK only, free) – genuinely useful context beyond 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?

Front-loaded with the core purpose, then edge cases, then scope, then the prerequisite workflow – a sensible order with no filler. It is slightly dense and could trim a clause, so 4 rather than 5.

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 and rich annotations already present, the description only needs to add purpose, edge cases, and prerequisites – and it covers all three. An agent has everything required to select and invoke it correctly.

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. It does: it clarifies the tool is 'keyed on a UPRN, not an address' and points to address_autocomplete/address_resolve to obtain the value, which is exactly the missing semantics. It does not describe the integer format or constraints, keeping it below 5.

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+resource (carries the property's own last registered sale to today via a repeat-sales index) and enumerates the outputs (price paid, date, index factor, anchored value). This is clearly distinguishable from siblings like transactions_by_uprn, time_adjustment, and valuation_estimate without opening any 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 concrete when-to-use context ('the strongest single piece of evidence a valuation has') and an actionable prerequisite chain: call address_autocomplete to narrow, then address_resolve to obtain the UPRN. It does not explicitly contrast with alternatives like transactions_by_uprn or time_adjustment, so it stops at 4 rather than 5.

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