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

With no annotations, the description carries the full behavioral burden. It does disclose genuine behavioral facts an agent would otherwise miss: results are ordered newest first and each call costs 1 credit, which is a real cost/rate consideration. It stops short of explaining what happens with zero filters, whether results are capped at the 1-200 limit by default, or how the external Land Registry lookup behaves on failure.

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?

A single sentence that front-loads the data source, then the query axes, then the return fields, then the credit cost. Every clause adds information and nothing is repeated from the schema or title.

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?

The description covers the return shape well in the absence of an output schema, listing price, date, type, tenure and new build. However, for a tool with six optional parameters and no annotations, it omits the semantics of the date floor ('from') and the price floor ('minPrice') and gives no fallback behavior for an unfiltered call, which an agent needs in order to invoke this safely.

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 100%, so the six parameters are already documented in structured form and a baseline of 3 is appropriate. The description adds meaning for three of them by naming postcode, town and street as the location axes, and implies ordering via 'newest first'. It says nothing about 'from', 'minPrice' or 'limit' beyond what the schema already states.

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?

The description names the specific dataset (HM Land Registry price paid) and specifies exactly what is queried (property sales by postcode, town or street) and what comes back (price, date, type, tenure, new build). It is clearly distinct from the only sibling, epc_search, which concerns energy performance certificates, though it does not explicitly say so. Purpose is unambiguous without opening the 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?

Usage is only implied: an agent can infer this is the lookup for sold-property prices in a given location. There is no statement of when to prefer it over epc_search, nor any guidance on the fact that all six parameters are optional — an agent cannot tell whether calling with no location filter returns the whole dataset or errors. The credit-cost note does help an agent weigh the call.

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