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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context the annotations cannot: costs are the assessor's model priced at the certificate's date rather than actual bills, which prevents an agent from presenting them as current running costs. It stops short of stating coverage limits, e.g. what happens when no certificate exists for the address.

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?

The subject is front-loaded ('A home's Energy Performance Certificate'), and every clause carries a distinct return field rather than filler. The main sentence is long and comma-chained, so the field list is slightly hard to scan, but no sentence is expendable.

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 no output schema, describing the returned fields is exactly the description's job, and it does so comprehensively, including the important caveat about cost modelling. What is missing is edge-case behavior — absent certificates, partial data, or cost of the lookup — for a tool whose only input arrives from another call.

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% and the single akey parameter is documented there, including its origin in search_addresses and its hex pattern. The description adds no further meaning about akey, so the baseline of 3 applies; the schema is doing all the parameter work.

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 enumerates exactly what the tool yields for a single home: current rating and score, potential rating, modelled running costs for heating/hot water/lighting, CO2, weak building elements, and assessor improvement list. That is specific and far beyond the title. It does not, however, name any sibling it differs from, and it never states the verb (retrieve/fetch) explicitly — the action is inferred from the inventory of fields.

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?

There is no when-to-use framing: nothing says to call this for a single property rather than compare_homes or get_address, and no prerequisites are given (e.g. that an akey must first come from search_addresses). The usage context is only implied by the phrase 'A home's', which is too thin for a lookup tool surrounded by many address-oriented siblings.

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