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

Annotations already declare the read-only, idempotent, non-destructive profile, and the description goes well past them: it flags beta status (every response returns beta: true and a beta_notice), discloses a 20¢ per-call charge, specifies ordering (nearest first) and the per-field provenance taxonomy (measured / measured_wider_area / estimate / not_recorded) plus the `how` sentence. That is exactly the kind of cost, confidence, and interpretation context annotations cannot carry.

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?

Content is front-loaded (beta warning first, then the topic question, then the return shape, then provenance, then price), so an agent can stop reading at any layer. Some belt-and-braces repetition exists — beta is signalled in the title, the opening note, and the response field — but the length is justified by the number of distinct disclosures.

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?

There is no output schema, yet the description fully covers the response: the `mesh_blocks` array, per-entry fields (mb_code, distance_m, population, dwellings), sorting, cross-boundary inclusion, and the provenance/how labeling an agent needs to interpret values honestly. Combined with the beta and pricing disclosures, nothing material is missing for correct invocation.

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 single parameter has 0% schema description coverage, so the description must carry the load; it does clarify that the identifier is a property key by referencing `/properties/{gnaf_id}/context/mesh-blocks` and by scoping results to "around the property." It never states the expected format of a gnaf_id or where to source one, which leaves a real gap for a required identifier.

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+resource in a plain question ("How big are the blocks of land?") and enumerates exactly what comes back: median and spread of lot sizes, lot shape, floor space ratio, minimum lot size, parcel counts, one entry per mesh block within 1,000 m. It also explicitly carves out the sibling boundary ("Values only — the polygons come from /properties/{gnaf_id}/context/mesh-blocks"), so an agent can separate it from properties_context_mesh_blocks and the building/business siblings without opening a 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?

The scope condition ("for every mesh block around the property", within 1,000 m, including blocks across suburb lines) tells the agent when this tool is the right fetch, and the polygons note tells it when a sibling is. However, there is no explicit exclusion against the near-named alternative properties_surroundings_parcels, and no stated prerequisite for obtaining a gnaf_id.

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