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

Annotations already cover read-only, idempotent, non-destructive and closed-world, and the description adds substantial data-quality disclosure beyond them: a four-value provenance taxonomy explaining when a number is measured at the block versus repeated from an SA1/postcode versus modelled, plus the `how` sentence and its empty-when-not_recorded rule. It also clarifies that this endpoint returns values only and that its geometry companion lives elsewhere, which prevents a common misread.

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?

The bolded lead question front-loads purpose, followed by payload contents, response shape, and the provenance legend in a logical order. It is dense but nearly every clause carries distinct information; the only slight redundancy is restating that values come from this endpoint while polygons come from the shapes route.

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 still specifies the response envelope (a `mesh_blocks` array), its per-entry keys (mb_code, population, dwellings), and the per-field provenance annotations. For a one-parameter read tool whose annotations already establish safety, the remaining gap is only response size for large suburbs, which is minor.

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?

The single suburb_name parameter has 0% schema description coverage, so the description carries the burden, and it only alludes to the parameter via 'in the suburb'. It does not state whether the name must be exact, how ambiguity between same-named suburbs is handled, or what happens for an unknown suburb, leaving the agent to guess at format.

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 opening line plus the enumerated payload (advertised weekly rent median/range/count/year, our estimate, gross yield, and surrounding-area median) states a specific resource at a specific grain: one entry per mesh block in the suburb. It is clearly distinguishable from suburb-level siblings like suburbs_market_median_rent or suburbs_market_yield_pct because it names the mesh-block grain and the mb_code key.

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: 'for every mesh block in the suburb' signals this is the granular alternative, and the note that polygons come from /shapes/mesh-blocks correctly routes the agent to suburbs_shapes_mesh_blocks for geometry. However, there is no explicit guidance on when to prefer this over suburbs_market_median_rent, suburbs_market_rent_map, or subdivisions like suburbs_mesh_blocks_tenure, and no stated prerequisites or input format expectations.

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