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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the description need only add behavioral detail. It does: results are capped to the newest 2,000 applications, every mesh block is returned with 0 where there were no applications, and only values are returned with no polygons attached. The only omission is the key/identifier used for joining values to geometry.

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?

Four short sentences with good density: the count definition and cap come second, with scope and zero-fill established immediately. The leading sentence about the report card and map layer is oriented toward the UI rather than the agent, so it earns slightly less place than the rest, but nothing is truly wasteful.

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?

For a single-parameter, no-output-schema aggregate tool, the description covers the important non-obvious facts: the 2,000-application window, the zero-filled block list, and the values-only return that must be joined to shapes. What remains unstated is the mesh-block identifier used for that join and the units/type of the values, which is a moderate gap for a map-layer endpoint.

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 one required parameter, suburb_name, with 0% schema description coverage; the description only says 'of the suburb' and adds no format detail (suburb name vs. ID vs. postcode, or disambiguation for duplicate names). The single, self-descriptive parameter keeps the cost low, but the description does not compensate for the schema gap.

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 precisely what is measured — counts of new-dwelling development applications per mesh block for a suburb, capped at the newest 2,000. It also separates the data from its companions (individual applications at /development/applications, geometry at /shapes/mesh-blocks), though it references them by API path rather than by sibling tool name, so the mapping to tools like suburbs_development_applications is inferred rather than stated.

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 through the data-composition notes: use this for per-block counts, use /development/applications for individual records, and /shapes/mesh-blocks for polygons. There is no explicit statement of when to prefer this over near-siblings such as suburbs_development_da_count, suburbs_development_applications, or suburbs_mesh_blocks_signals, and no exclusions or prerequisites.

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