City boundary

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so safety is covered. The description adds real behavioral context beyond them: geometry is thinned to `max_points` per ring so the shape is approximate, and the returned payload differs sharply between the two modes. It stops short of mentioning error behavior for an unknown district or coordinate order caveats beyond [lon, lat].

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 tight sentences, with the resource and the two output modes front-loaded before the usage and next-step guidance. Slightly dense in the first clause, but no filler or repetition of schema content.

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 carries the return-shape burden and does so adequately by naming the bounding box tuple, the per-neighbourhood id/centre/box fields, and the GeoJSON Feature shape. Missing only failure modes (unknown city/district) and any note on coordinate reference system beyond the [lon, lat] ordering.

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 100%, so the baseline is 3, but the description adds genuine semantic weight: `district` is framed as a mode switch, not just a filter, and `max_points` is explained as a lossy approximation of the outline rather than a raw cap. `limit` is not clarified further in the description, which keeps this from a 5.

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 (neighbourhood borders of a city) and source (Divar's GeoJSON), then splits the two operating modes explicitly: no `district` returns the city bounding box plus a neighbourhood list, with `district` returns one neighbourhood's GeoJSON Feature. An agent can distinguish this from dv_districts, dv_neighbours, and dv_locate without reading any 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?

Gives a concrete use condition ('draw an area or test a point against it'), an explicit exclusion with the alternative ('for a point's own neighbourhood use dv_locate'), and a forward pointer ('Next: dv_nearby with the centre'). Routing between siblings is fully specified.

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