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

Annotations already cover read-only, idempotent, non-destructive and closed-world, but the description adds genuinely new behavior: a 20¢ per-call price, one entry per mesh block ordered nearest first, cross-suburb inclusion, and a provenance taxonomy (measured / measured_wider_area / estimate / not_recorded) with a `how` sentence explaining derivation. The measured_wider_area caveat in particular warns the agent that repeated values across blocks are not block-level measurements, which prevents a serious misinterpretation.

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 guiding question, then scope, then output shape, then provenance, then price — a sensible priority order with no filler sentences. Slightly dense, and the provenance paragraph is long, but every clause conveys information an agent would otherwise have to guess.

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 must describe the return payload, and it does: the `mesh_blocks` array, per-entry mb_code, distance_m, population, dwellings, the metric set, ordering, and the provenance/how fields. Combined with annotations and the cost disclosure, an agent has everything needed to call it and interpret results correctly.

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 0% for the single `gnaf_id` parameter, so the description carries the burden. It implies the parameter identifies a property via the endpoint path `/properties/{gnaf_id}/context/mesh-blocks` and that all results are relative to it, but it never states the identifier's format, source, or what happens for an unknown ID. Partially compensating, not fully.

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 concrete verb-and-resource pair: for every mesh block within 1 km of a property, return counts of properties, share of houses vs strata, median bedrooms/bathrooms/building size, height and recent construction. It also scopes itself against a sibling concern by noting that polygons come from the context/mesh-blocks endpoint and that this tool returns values only, so an agent can distinguish it from properties_context_mesh_blocks and from the suburb-level suburbs_mesh_blocks_building.

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 context is clear: per-property, per-mesh-block building profile within a 1,000 m radius, nearest first, including blocks that cross suburb lines. The pointer that polygons live elsewhere acts as a routing hint away from a sibling. However, it never explicitly names an alternative tool or states a when-not condition (e.g., use suburbs_mesh_blocks_building for suburb-wide aggregates), so the agent must infer the boundary.

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