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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, consistent with 'UK only'. The description adds real value beyond that: cost, null-handling for `year_built` and `num_floors`, 0.5 m simplification of the outline, attribution preservation, and the caveat that extrusion is massing-only. However, one important behavioral trait is missing: the description never states any limit on how many UPRNs may be batched per call, so an agent cannot predict the cost or failure mode of a large request.

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 short paragraphs, front-loaded with the resource and its fields, then data-quality caveats, then usage rules. Every sentence is informative, though the extrusion caveats (no facades, no internal boundaries) sit at the tail and could be tighter for a description that is already long.

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 values need not be explained; the description instead supplies the operational context an agent needs — geography, cost, prerequisite resolution chain, null semantics, and how to consume the GeoJSON correctly (use building_height_m, not altitude). Nothing material is missing for a single-parameter read 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 sole parameter is a bare integer array with no description, so the description must carry the load. It does much of that: 'a set of UPRNs' conveys batch semantics, 'keyed on a UPRN, not an address' rules out the wrong identifier type, and it points to the tools that produce valid values. It stops short of stating per-call caps or ordering, which is the remaining gap.

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 resource (physical form of the buildings a set of UPRNs sit in) and enumerates exactly what comes back: height, volume, footprint area, floor count, materials, basement, green roof, solar, unit mix. This clearly separates it from siblings such as energy_profile, solar_potential or property_summary without needing their schemas.

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?

Explicit routing: UK only, keyed on UPRN rather than address, and a named two-step path (free `address_autocomplete` to narrow, then `address_resolve` to obtain the identifier). It also states the cost (15 credits / 15p), letting the agent weigh the call before making it.

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