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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds traits the agent cannot get from them: a per-call price of 30¢ and, crucially, the provenance taxonomy (measured / measured_wider_area / estimate / not_recorded) with a `how` string, which tells the agent how far to trust each number. That is substantive disclosure well beyond the annotations.

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 question it answers, then scope, then field-level detail, then price — a sensible ordering. It is moderately long with markdown emphasis, but nearly every clause (distance ordering, suburb-line behaviour, provenance categories, cost) carries information the caller needs.

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?

No output schema exists, so the description carries the return contract and does so thoroughly: top-level `mesh_blocks` array, per-entry mb_code, distance_m, population, dwellings, ordering, and the provenance/how semantics on every value. For a read-only single-parameter lookup, nothing material is missing except GNAF ID acquisition, which the schema gap already captures.

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?

There is one required parameter with 0% schema description coverage, so the schema gives no help. The description only conveys its meaning indirectly through the path template '/properties/{gnaf_id}/...' and the title's '(by gnaf_id)'; it never says what a GNAF ID is, where to obtain one, or whether a property address can be substituted.

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 (advertised weekly rents, our rent estimate, gross yield per mesh block within 1 km of a property) with a concrete framing question. It also explicitly bounds itself against the companion tool: 'Values only — the polygons come from /properties/{gnaf_id}/context/mesh-blocks', so an agent can separate it from properties_context_mesh_blocks and from the suburb-scoped suburbs_mesh_blocks_rent.

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?

Scope is spelled out precisely: one entry per mesh block within 1,000 m, nearest first, blocks across suburb lines included, and the polygon/values split routes the agent to the right sibling. It does not state when *not* to use it (e.g. suburb-level rent → suburbs_mesh_blocks_rent, or time series → properties_rent_history), so the alternative side of the decision is left implicit.

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