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

Annotations already establish readOnly/idempotent/non-destructive, and the description layers on genuinely useful behavioral context: a null gain means no recorded sale rather than zero, the gain is nominal not inflation-adjusted, coverage is UK-only and free. This directly shapes how the result should be interpreted and reported.

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?

Well front-loaded: the positive definition comes first, then the negation, caveat, and routing. The 'saying so is part of reporting it honestly' aside is slightly editorial, but every sentence carries a distinct constraint and nothing is redundant.

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 structure needn't be restated, and the description fills the remaining gaps an agent needs: null semantics, nominal-vs-real framing, geographic scope, cost, and the UPRN acquisition path. Nothing required to call it correctly is missing.

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 lone 'uprns' parameter, so the description must carry the meaning — and it does, clarifying the key is a UPRN rather than an address and pointing to the resolver tools. Minor gap: the schema types the field as an array while the prose speaks of 'a UPRN', leaving batch semantics unstated.

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 computed output: current estimated value against the last recorded sale, expressed as gain in pounds and percent plus holding period. It explicitly negates the nearest misinterpretation (loan-to-value / equity net of debt), which separates it from valuation_estimate and related siblings at a glance.

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 the exact precondition and workflow: keyed on a UPRN, so call address_autocomplete to narrow then address_resolve to obtain one. Also supplies a reporting guideline (call it NOMINAL, don't imply inflation-adjusted real return), which is when-to-use guidance beyond mere invocation.

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