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

Annotations already establish a safe, idempotent, closed-world read, so the bar is lower, and the description still adds substantial context: the dataset is beta, every response carries beta: true and a beta_notice, and each field carries a provenance tag with defined meanings (measured, measured_wider_area, estimate, not_recorded) plus a 'how' sentence. That is genuinely useful behavioral disclosure beyond the annotations. It omits practical traits such as response size for blocks with many rows or behavior for an unrecognized suburb.

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 beta caveat is front-loaded, followed by the purpose question and then the return shape, which is a sensible ordering for an agent deciding whether to call. The beta paragraph is somewhat verbose relative to the rest, but each part conveys material information rather than restating the title.

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?

With no output schema, the description correctly takes on the job of explaining returns: one entry per mesh block under mesh_blocks with mb_code, population and dwellings, values only, and per-field provenance. That is enough for an agent to call and interpret the result. Missing only operational details like payload size for dense suburbs and failure behavior for an unknown suburb name.

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, and schema description coverage is 0%, so the description must carry the burden. It only implies the parameter's meaning through 'in the suburb' and gives no format, matching, or normalization guidance (e.g., whether to resolve via geocode_suburb first). The single-sentence framing does not fully compensate for the undocumented schema.

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 specific resource (per-mesh-block signals for a suburb) and enumerates the measures returned: recent price growth versus suburb, long-run house value growth, and share recently listed for rent. An agent can see this is a mesh-block-level market-movement tool, distinct from suburb-level tools like suburbs_market_price_growth. It does not explicitly name a sibling it differs from, so it stops short of a 5.

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 by the framing question 'Is this block moving?' plus the note that only values are returned and polygons come from /shapes/mesh-blocks, which quietly steers an agent away from expecting geometry. There is no explicit when-to-use/when-not statement, no mention of alternatives such as suburbs_market_recent_price_movement for a suburb-level answer, and no prerequisite about how suburb_name must be supplied.

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