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

Annotations already cover read-only, idempotent, non-destructive, and closed-world; the description adds materially more: a 20¢ per-call price, a 1 km radius, nearest-first ordering, inclusion of blocks across suburb lines, and a per-field provenance taxonomy (`measured`/`measured_wider_area`/`estimate`/`not_recorded`) with a `how` explanation. That provenance vocabulary is exactly the kind of epistemic disclosure an agent needs in order to trust the numbers, and it is not derivable from annotations or schema.

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 a bolded intent question, then scope, then return shape, then provenance semantics, then price, which is a sensible order. The one wasted element is the rhetorical headline; the rest is dense and each sentence carries new 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?

With no output schema, the description carries the burden of describing the response and does so: one entry per mesh block with `mb_code`, `distance_m`, `population`, `dwellings`, plus per-field `provenance` and `how`. Only the identity/format of `gnaf_id` is left unstated, which is a small gap for a single-parameter read tool.

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 parameter, `gnaf_id`, with 0% schema description coverage, so the description needs to do the work. It shows `gnaf_id` only inside the path template `/properties/{gnaf_id}/context/mesh-blocks`, from which the agent can infer that it is a property identifier, but it never states the format or how to obtain it. Coverage is therefore partial, not compensating.

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 title and opening sentences state a specific resource (Financial-stress indicators of mesh blocks within 1 km of a property) and enumerate the metrics: unemployment, JobSeeker recipients, mortgage arrears, forced sales, and insolvencies. The `(by gnaf_id)` anchor in the title, together with the reference to `/properties/{gnaf_id}/context/mesh-blocks`, distinguishes it from the `suburbs_*` siblings, but the description never names the alternative scope explicitly.

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 "Is anyone here under financial pressure?" implies the use case (assessing neighborhood financial stress around a specific property), and the note that polygons come from the context/mesh-blocks endpoint tells the agent how to get the matching polygon. There is no explicit when-not-to-use guidance or named alternative such as `suburbs_mesh_blocks_stress`, so the agent must infer that this tool differs from it by scope.

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