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

Annotations already establish read-only, idempotent, non-destructive, closed-world behaviour, so the bar is lowered, yet the description still adds non-obvious context: the values are a projection rather than an actual election result, and the payload contains values only with no geometry. That second point is materially useful because it tells the caller a separate join is required, which no annotation conveys.

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?

Three short paragraphs do a lot of work and are front-loaded with the map label and then the data description. The one redundancy is restating the UI label and the description title, but that framing helps a caller match tool to UI output.

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, read-only, annotation-covered tool with no output schema this is close to complete: it says what the data is, that it is a projection, and that geometry is elsewhere. The missing piece is parameter semantics, plus the absence of any note on granularity limits (mesh-block count/volume) that would matter for a suburb-wide map 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 schema declares a single parameter, but the description never explains what a suburb maps to in this API — the only concrete nouns used are the path and the label. The schema has 0% description coverage and the description does not compensate, so an agent must infer how to obtain the suburb value (e.g. from the listing/search tools).

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 names a specific resource and scope: projected winning party, runner-up and margin for every mesh block in a suburb at a projected May 2026 federal election, delivered as the 'Voting (winning party)' map layer. It also implicitly distinguishes itself from the suburb-wide profile variant by pointing at `/suburbs/demographics/voting`, though it does so by endpoint path rather than by sibling tool name, so an agent must translate that into the underscore-named sibling.

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: the reader learns this is the map/report layer and that the suburb-wide equivalent lives at `/suburbs/demographics/voting`, and that polygons must come from `/shapes/mesh_blocks`. There is no explicit when-to-use/when-not statement and no sibling tool names, so an agent must infer that `suburbs_shapes_mesh_blocks` is the required companion and that the non-map tool is the alternative.

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