Reverse geocode a point

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

Annotations already declare read-only/idempotent/non-destructive, and the description still adds substantial behavior beyond them: a documented degraded result (source: "divisions_only" plus a note) when the addresses theme is unreachable or lacks coverage, a structured {"error": ...} return instead of a raise, and the omission-instead-of-null rule for country/region. This is exactly the extra context annotations can't carry.

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?

The input→output contract is front-loaded in the first sentence, followed by degradation and error semantics. Slightly wordy phrasing ("so this is the expected degraded path") costs a little, but nearly every sentence carries load-bearing information.

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 a two-parameter tool with an output schema, the description is more than sufficiently detailed: it explains degraded output, error shape, and field-omission rules. The only real gap is sibling differentiation (batch vs single vs address_at), which the usage dimension already penalizes.

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% for the two parameters, so the description would need to compensate — but it only implies a point via "Point ->", adding no coordinate-system, precision, or ordering detail. lat/lon are near-universally understood, so the gap is minor, but the description contributes little here.

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 opening line states a precise input→output transformation: a point in, the nearest street/number/postcode plus its containing division chain out. This is a specific verb+resource that an agent can tell apart from forward geocoding siblings like geocode or geocode_address without opening a schema.

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 description (point-based reverse lookup), but it never says when to prefer this over siblings such as address_at, reverse_geocode_batch, or admin_lookup, nor any exclusions or prerequisites. The conditions described (degraded path, error path) are behavioral, not selection guidance.

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