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

Annotations already declare a safe read-only, idempotent operation, so the description's real value is the data-quality disclosure: provenance labels including measured_wider_area (SA1/postcode value repeated on every block) and not_recorded, plus a per-field `how` sentence. The measured_wider_area caveat materially prevents an agent from over-reading block-level precision. It does not cover response size or how many blocks a suburb can return.

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 bold framing question, then scope, then return shape, then a caveat paragraph — a sensible ordering with no filler sentences. The bold question is slightly promotional but earns its place as a use-case cue; the rest is dense and specific.

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 naming the `mesh_blocks` collection and its per-block fields (mb_code, population, dwellings) and the provenance/how metadata attached to every value. Missing pieces are secondary: no indication of expected result volume or whether the whole suburb is returned unpaginated, and no suburb_name input format.

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?

Schema description coverage is 0%, so the description carries the full burden for the single required parameter, and it supplies nothing: no format ('Suburb, STATE' vs bare suburb), no case sensitivity, no disambiguation guidance for duplicate suburb names. The phrase 'in the suburb' only restates the parameter name. This is a clear gap despite the parameter being few in number.

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 verb-and-resource scope: per-mesh-block hazard exposure (flood planning/overlay, bushfire-prone, erosion-prone), risk scores for flood/fire/coast/ground movement, and slope. The distinction from polygon data is made explicit ('Values only — the matching polygons come from /shapes/mesh-blocks'). It stops short of distinguishing itself from close siblings such as suburbs_mesh_blocks_environment, suburbs_risks_flood or suburbs_shapes_hazards, which an agent must infer.

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?

It provides one implicit routing rule — use this for values, use /shapes/mesh-blocks for the matching polygons — which is genuinely useful. There is no explicit when-to-use guidance versus the many other hazard/risk siblings (suburbs_risks_all, suburbs_mesh_blocks_environment), and no stated prerequisites such as needing a resolved suburb name from geocode_suburb.

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