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

With zero annotations, the description carries the behavioral disclosure burden. It clearly communicates scope (suburb area vs properties), the geojson optional behavior, and offers a mental model of how area and property counts diverge. It does not disclose error cases or rate limits, but for a simple read-endpoint that is acceptable.

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 description is focused, front-loaded with the core metric, and uses a short example to make the key distinction concrete. The pointer to the sibling is arguably a third sentence that could be trimmed, but it pays for itself by preventing tool mis-selection, so it 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?

Given the tool is a simple two-parameter read, the description already covers the meaning of the return value, the parameter effect (`geojson=true`), and the main confusion with the property-count sibling. It does not need to explain output shape because an output schema exists. Minor gaps like boundary edge cases are not essential 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?

The `geojson` parameter is already well documented in the schema, and the description adds context for interpreting the result. Since it clarifies `suburb_name` semantics indirectly through the AREA-vs-property distinction and the example, it adds meaningful interpretive value without padding. The 50% schema coverage is compensated by the description not being a tautology.

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 clear metric ('Share of the suburb AREA covered by bushfire-prone designation'), explicitly distinguishes area-based from property-based counts, and gives a concrete example. It immediately differentiates this from `properties_risks_bushfire` and related risk siblings.

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 explicitly warns the metric is area-based, not property-based, and names the exact alternative (`GET /v1/suburbs/{suburb_name}/risks/property-hazard-counts`) for property-level figures. The 'If you want...' conditional gives the agent a clean rule for when to pick the sibling instead.

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