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

Annotations already declare the safe, idempotent, non-open-world read profile, so the description only needs to add context. It does add the data provenance ('official open data') and the response shape ('for each kind the count, the nearest one and its distance'), which matters since there is no output schema. However, the 'expanding rings up to 16 km' detail is already stated in the `closest` schema field, and the description says nothing about empty-result behavior, coverage limits, or cost/latency of the wider search.

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?

Two sentences, front-loaded with the amenity categories and radius before the alternate mode, with no filler. The long category enumeration is dense but it is load-bearing, since the `closest` enum is not visible at a glance in prose otherwise. Slightly overstuffed in a single sentence, but nothing is wasted.

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 correctly spends its budget describing the return value (count, nearest place, distance per kind). It covers both operating modes and the radius bounds. It is not fully complete: it does not say what happens when nothing is found within the radius, nor how counts behave when `closest` is set.

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 75%, so the schema already documents `akey`, `radius_m`, and the enum values for `closest`; baseline is 3. The description reinforces the purpose of `closest` (nearest N of one kind instead of counts) but adds no new syntax or constraint detail for `n` or `radius_m` beyond what the schema states.

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 concrete resource set (rail/tram/ferry/bus stops, schools, cafes, pubs, takeaways, supermarkets, parks, playgrounds) and the scope (around one home, from official open data, 100 m to 2 km), plus the exact return shape per category. That is far more specific than the bare title 'What is nearby'. It stops short of a 5 because it never contrasts itself with nearby-scoped siblings such as area_overview or district_statistics, leaving the agent to infer the distinction from name alone.

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 rather than stated: the agent can infer it is for point-level amenity lookup given a single address key. The one explicit routing rule is the alternate mode — 'Pass `closest` with a kind to get the nearest N of that kind instead' — which is genuinely useful. There is no guidance on when to prefer this over area_overview or address_report, and no prerequisite/exclusion guidance.

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