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

Annotations already cover the read-only/idempotent safety profile, and the description adds material context beyond them: the 10-credit cost, UK-only coverage, the repeat-sales index fallback chain (district → local authority → national), the `index_unavailable` carry-receipt behavior, and an explicit disclosure that the -10% relisting penalty is an assumption rather than a measured discount.

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 outcome ('The evidence behind a valuation, itemised') and every clause earns its place, but the return-value, penalty, fence, cost, coverage and prerequisite facts are compressed into one dense paragraph of nested parentheticals that is harder to scan than it needs to be.

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 3-param read-only tool with an output schema, the definition supplies everything an agent needs to call it correctly: identity key, optional-param semantics, range limits, cost, geographic scope and the prerequisite lookup path. The output schema handles the return shape, and the description still usefully previews it.

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 carries the full burden and does: uprn is 'keyed on a UPRN, not an address' with the route to obtain one; relisted_uprns gets meaning, the condition to pass it and its assumption status; lookback_months gets an explicit 12–120 range not present in 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?

States a specific verb+resource ('same-building comparable sales ... itemised' with time adjustments) and explicitly distinguishes itself from the sibling `valuation_full` ('gives the value itself'). An agent can tell this apart from valuation_comparables, property_comps and time_adjustment 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?

Explicit when-to-use ('show WHY a value is what it is') with the named alternative ('valuation_full gives the value itself'), plus a prerequisite workflow (address_autocomplete → address_resolve to obtain a UPRN) and a conditional rule for when to pass relisted_uprns. Nothing is left to inference.

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