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 real value beyond them: it discloses the response shape (one entry per mesh block under mesh_blocks with mb_code, population, dwellings) and a four-way provenance taxonomy including measured_wider_area, which warns the agent that some figures are repeated from SA1/postcode level and are not block-specific. That caveat is exactly the kind of context that prevents misinterpretation; only pagination, limits and cost/auth are unmentioned.

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?

Three short blocks: a framing question, a scope/return statement, and a provenance legend. The provenance paragraph is dense but earns its length because it prevents misreading repeated wider-area values as block-level measurements. Minor waste in the rhetorical question, but it front-loads the purpose effectively.

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 does the necessary work of describing the return payload, its per-block keys, and the meaning of provenance/how fields, and it points to /shapes/mesh-blocks for geometry. The remaining gap is input-side: how to correctly specify suburb_name and what happens when the suburb is unknown or ambiguous.

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 a single required parameter, suburb_name, with 0% schema description coverage, so the description carries the full burden — yet it only says 'in the suburb' without clarifying whether the value is a name, a slug, or an ID, how ambiguous names resolve, or whether the postcode mentioned in the text is an alternative input. The one parameter an agent must supply is effectively undocumented in both places.

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 concrete resource and scope: tenure shares, median mortgage repayment, rental listing share and rent assistance, computed for every mesh block in a suburb. The bold lead-in 'Who owns and who rents here?' plus 'For every mesh block in the suburb' makes the granularity explicit. It never names the near-siblings (suburbs_demographics_tenure at suburb level, properties_surroundings_tenure at property level), so an agent must infer the difference from scope wording alone.

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 is implied rather than stated: the framing question suggests investigative/area-profiling queries, and the note that polygons come from /shapes/mesh-blocks implicitly routes geometry requests elsewhere. There is no explicit when-to-use, when-not-to-use, or named alternative, and no prerequisite such as resolving the suburb first.

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