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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the description's job is to add context — and it does: ACS 2020-2024 vintage, HM Land Registry sale prices for a trailing 12 months, and the fact that coverage is limited to US and UK geographies with England-only deprivation deciles. It omits failure behaviour (unmatched address, non-US/UK location), so it is strong but not complete.

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 lead sentence is well front-loaded, but the remainder is a single sprawling list of metrics joined by semicolons and commas rather than structured by country. Because there is no output schema, listing the fields earns its place, but the run-on formatting makes it 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?

With no output schema, the description carries the return-value burden and discharges it thoroughly, including data vintages and the US/UK split of what comes back. The remaining gap is operational: nothing about error handling or what happens when an address cannot be resolved to a tract, ward or postcode sector.

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 schema already explains lat/lon/address/country and their mutual exclusivity; the description adds nothing about formats or precedence beyond that. The only marginal value is signalling that the returned data shape depends on whether the address resolves in the US or UK, which indirectly motivates the country hint.

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 'Who lives around an address' gives a concrete verb-like framing and the resource is unmistakable, then the body enumerates exactly which demographic, deprivation and price fields come back. It never names a sibling such as home_buyer_report or listing_location_pack, so an agent must infer the boundary itself, which keeps it short of a 5.

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 by 'around an address' and by the US/UK data split; there is no statement of when to prefer this over home_buyer_report, crime_nearby or schools_nearby, and no prerequisites or exclusions. An agent can guess the intent but gets no routing guidance.

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