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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: UK-only scope, a 15-credit/15p cost, the UPRN keying requirement, and a detailed semantic layer distinguishing predictions from measurements and declaring that EPC habitable rooms are not bedrooms and occupier tenure is not legal tenure. That is exactly the kind of interpretive context an agent cannot get from structured fields.

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 scope and the pre-valuation review instruction are front-loaded, and the back half is a dense but purposeful list of interpretation rules with no filler. Some sentences pack multiple caveats together, which slightly hurts scannability, but no clause 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?

An output schema exists, so return-value documentation is not required, yet the description still explains how to read key result flags (eligible_as_primary: false, imputed, ml_primary) and what to do with user confirmations. Geography, cost, prerequisite tooling and data-provenance caveats are all present for a one-parameter tool.

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% and the single integer parameter has no description, so the description must carry the meaning — and it does, stating that the tool is keyed on a UPRN rather than an address and naming the two sibling tools that produce one. It does not specify the UPRN format or an example value, but the semantic gap is otherwise well compensated.

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 opening line plus title establish that this returns cross-source property facts with provenance and unresolved attributes for a single UPRN, which is a specific output shape an agent can distinguish from property_summary or property_lookup. It stops short of stating the reconciling/merging action as a verb, so the agent must infer that the value is in adjudicating conflicting sources rather than just listing facts.

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?

It gives a concrete invocation context ('Review floor area, bedrooms and tenure with the user before a valuation') and a full prerequisite chain: address_autocomplete to narrow, then address_resolve for a UPRN. It also implicitly rules out address-keyed calls. What is missing is explicit guidance on when to prefer this over sibling fact tools such as property_summary or property_report.

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