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

Annotations already declare this as a safe, idempotent, non-destructive local read, so the bar is lower. The description still adds real behavioural content beyond them: the distance is straight-line rather than routed or travelled, units are metres, coverage is England with GB stops where published, the call is free, and two known data gaps (catchment, school phase) are disclosed.

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 and front-loaded, one long first sentence carrying scope and output, followed by short caveat fragments. The telegraphic style ('Free.', 'England (stops GB where published).') is efficient but slightly clipped, and none of it is filler.

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 no explanation, and the read-only annotations cover safety. However, with five parameters and none required, an agent gets no guidance on which of land_id, location or postcode to supply or whether they can be combined — a meaningful omission for correct invocation.

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 0%, so the description must carry the load. It does enumerate the kinds enum values in prose and explains the distance metric, but it says nothing about per_kind's meaning or default, nor about how land_id, location and postcode relate to each other, which matters because zero parameters are required.

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 the exact resource set (bus stops, rail stations, metro/tram, ferry terminals, open schools), the measurement (straight-line, in metres) and the return payload (names plus NaPTAN or school references). No sibling tool covers transport/school proximity, so the purpose is unmistakable, though the description never explicitly contrasts itself with neighbours such as area_report or site_appraisal.

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 implied by the scope: use it when you need proximity of stops and schools to a site. It adds useful guardrails ('a school catchment is not a distance', England-only coverage, GB stops where published) but gives no explicit when-to-use trigger and names no alternative tool for the catchment question it disclaims.

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