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

Annotations are absent, so the description carries the full burden. It does disclose the most important behavioral trait — that it returns values only and not geometry, routing the agent to /shapes/mesh-blocks for polygons. But it stops there: no mention of output cardinality, ordering, or any other operational detail, leaving the behavioral picture only partially painted.

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?

Two tight sentences with no filler. The core purpose is front-loaded (median house price per mesh block), and the critical 'values only — polygons from /shapes/mesh-blocks' constraint opens the second sentence. Every phrase (modal street, dearest/cheapest pockets, values-only) earns its place.

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?

An output schema exists, so return-value structure is covered elsewhere, and the description does convey the data content and the geometry-pairing workflow. However, the missing parameter format guidance and the absence of explicit usage guidance versus sibling median-price tools leave the definition not fully self-sufficient for a correct call.

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% and there is a single parameter, suburb_name. The description's 'in the suburb' phrase loosely ties the parameter to its role, but gives no format guidance (e.g., 'Bondi NSW' suffix, casing), which an agent would need to call it correctly. At 0% coverage the description must compensate, and the minimal tie-in does not suffice.

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 resource ('median house price for every microburb (mesh block)') and the exact scope of its output (modal street name, dearest/cheapest pockets). The 'Values only' note plus the pointer to /shapes/mesh-blocks clearly differentiates it from geometry-returning map siblings and from the single-value suburbs_market_median_sale_price, so an agent can tell them apart without opening the schema.

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 context is implied: it is a per-mesh-block map tool, and the note that polygons come from /shapes/mesh-blocks implies a pairing workflow. However, it never names the closest alternatives (suburbs_market_median_sale_price or the _series variant) nor states explicitly when this tool should be chosen over them, leaving the selection to inference.

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