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

The annotations already declare read-only, idempotent, non-destructive, closed-world, but the description goes well beyond them: it defines three-valued results (present with coverage share and up to five graded features, absent with distance to nearest within 2 km, not_checked with an explicit reason), warns that not_checked is never a clean result, and states size/vertex limits plus pre-read refusal with no charge.

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?

Front-loaded with the purpose, then a clearly signposted THREE-VALUED block and a scope-rules block, so the agent can find the invocation constraints quickly. The long enumeration of designation layers is long but earns some of its space by telling the agent what coverage to expect; still, it could be trimmed or grouped.

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 an output schema present the description need not spell out return shape, yet it explains the three-valued semantics that the schema likely cannot convey on its own. The definition is complete for a read-only lookup, with the notable hole being the `types` and `include_features` parameters and the phantom lpa_code reference.

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%, so the description carries the burden and mostly succeeds: it explains buffer_m (0-2000), location as 'lat,lng', postcode, area_geojson (WGS84, max 150 km², 64 vertices) and land_id. It leaves `types` and `include_features` entirely unexplained and even references an `lpa_code` scope that does not exist in the schema, which is a meaningful defect for an API this flexible.

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 description names a specific resource (planning and environmental designations) and the geometry types it accepts (red line, land parcel, point), and enumerates the layers covered, so an agent knows exactly what comes back. However, a close sibling named planning_designations exists and the description never distinguishes this tool from it, which keeps it off 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?

Strong operative guidance: 'Give exactly ONE scope', the five accepted scope forms with their formats, the UK-only constraint, and the statement that invalid input is refused before any read and nothing is charged. What is missing is routing advice against alternatives (planning_designations, property_flood_risk, planning_check), which an agent with this many siblings needs.

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