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 substantial value beyond them: it discloses that many values are actually measured at SA1/postcode level and repeated onto every block (measured_wider_area), that some values are modelled estimates, and that some are not recorded yet, each with a one-sentence `how`. That provenance taxonomy is exactly the kind of data-quality caveat an agent needs before quoting numbers; only error/absence behaviour is left unstated.

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 use-case question, then the metric list, then the response shape and provenance rules in short, well-separated sentences. The bold framing question is slightly promotional but earns its place as a selection cue; there is little other waste.

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 well: the `mesh_blocks` array, the mb_code/population/dwellings fields, and the provenance/how fields are all explained, plus the explicit pointer that geometry lives elsewhere. The remaining hole is input semantics for suburb_name and any failure/empty-data behaviour, which matters for a single required-parameter 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 required parameter, suburb_name, with 0% schema description coverage and no enum, and the description never mentions it — not its expected format, not whether it takes a name or code, and not how ambiguous or duplicate suburb names resolve. The phrase 'in the suburb' only implies the scoping dimension without adding any usable semantics.

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 description states a specific verb and resource: per-mesh-block financial-stress indicators (unemployment, JobSeeker, arrears, forced sales, insolvency) for a given suburb. It is clearly narrower than suburb-level siblings like suburbs_market_mortgage_stress or suburbs_demographics_unemployment, but it never names those alternatives, so the demarcation is inferred rather than stated.

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 analytical use case, and the note that polygons come from /shapes/mesh-blocks implicitly routes mapping work elsewhere. However, there is no explicit when-to-use, when-not-to-use, or named alternative for the overlapping unemployment/mortgage-stress siblings.

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