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

Annotations already declare a safe read-only, idempotent, closed-world call, so the bar is low – yet the description adds real behavioral context: a 20¢ per-call price, a 1,000 m radius, nearest-first ordering, inclusion of blocks across suburb lines, and a provenance taxonomy (measured / measured_wider_area / estimate / not_recorded) with the `how` explanation. These are facts an agent cannot get from the annotations or schema and materially affect whether and how to call it.

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 scope, then return shape, then provenance, then price – a logical progression with bold anchors. The opening rhetorical question is slightly decorative, and the provenance paragraph is dense, but no section is redundant.

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?

There is no output schema, so the description carries the full burden of describing returns – and it does: entry granularity, ordering, the per-block fields (`mb_code`, `distance_m`, `population`, `dwellings`), provenance semantics, and the pricing constraint. An agent can invoke this correctly and interpret the response without further documentation.

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 single `gnaf_id` parameter, and the schema only declares it as a string. The title and prose establish that it identifies a property ('by gnaf_id', 'around the property'), which is some compensation, but no format, source, or example of a G-NAF ID is given.

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?

Names a specific resource (transport metrics per mesh block around a property) and enumerates the exact contents: nearest bus stop, train station, tram stop, buses within 320 m, and public-transport commuting counts. It also bounds the resource precisely (every block within 1,000 m, nearest first) and separates itself from a complementary endpoint that supplies polygons.

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?

The framing question and 'For every mesh block around the property' make the intended context clear, and it explicitly routes polygon needs to `/properties/{gnaf_id}/context/mesh-blocks`, so the agent knows when not to use this call for geometry. It stops short of naming the suburb-level or property-level transport siblings, so the choice between this and `properties_transport_nearby` or `suburbs_mesh_blocks_transport` is left to inference.

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