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

Annotations already cover read-only/idempotent/non-destructive safety, and the description adds substantial extra context: 10-credit cost, UK-only scope, the buffered adjacency definition (strict touch finds nothing), the semantic caveat that 'no owner' means no linked title rather than nobody owns it, and the UPRN keying constraint.

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?

Dense but front-loaded, starting with what it returns before the mechanics and caveats. Every sentence adds information, though the definition runs long and the workflow sentence packs the cost/UK/keying facts together.

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 an eight-parameter aggregation tool, the description is complete: it covers identifier options, adjacency math, the high-level return shape (per-neighbour fields plus the combined block), caveats, cost and jurisdiction. An output schema exists, yet the description still orients the agent on what the combined block contains.

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?

With 0% schema description coverage, the description compensates well, explaining parcel_id/inspire_id/title_number/uprn as mutually exclusive subject identifiers, tolerance_m semantics (0.5 m default, why it exists) and ring_m control. However, limit and same_owner_only are never explained, leaving two of eight parameters undocumented.

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?

States a specific verb+resource: returns the parcels adjacent to one subject and who owns each, plus a combined assembly block. An agent can immediately tell this apart from parcel_lookup or owner_profile, and the description even routes to address_autocomplete/address_resolve for keying.

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?

Explicitly frames the tool as 'the first question of a site assembly' and gives a concrete pre-workflow (address_autocomplete free, then address_resolve to obtain a UPRN). It also tells the agent how to widen scope with ring_m and how to address the subject via four alternative identifiers.

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