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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely useful behavior beyond them: the minimum-one-filter constraint and the shape/ordering of the response ('Counts and pagination are returned ahead of the certificate list'), which an agent needs to parse results correctly.

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?

Three sentences, tightly front-loaded: what it searches, the constraint, then the return shape and the alternative tool. No repetition of the title or schema fields.

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 10-parameter search with no output schema, the description covers domain, scope, required-filter rule, response structure (counts/pagination then list) and the escalation path to get_certificate. An agent has everything needed to invoke and interpret 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 coverage is 100%, so baseline is 3, but the description contributes a cross-parameter constraint the schema cannot express (at least one filter required) and flags postcode as the common path, which helps prioritization among the ten optional parameters.

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?

Specific verb+resource with scope nailed down: 'Search the UK Energy Performance Certificate register for DOMESTIC (residential) properties in England and Wales.' The DOMESTIC/residential qualifier implicitly separates it from the non-domestic sibling, and it names the follow-up tool (get_certificate) for the full record.

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?

States the entry condition clearly ('At least one filter is required — postcode is the common case') and routes the agent to get_certificate when full technical detail is needed. It does not explicitly name search_non_domestic_epc as the alternative for commercial properties, leaving that disambiguation to the agent.

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