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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: national coverage of source data, an explicit not-found condition, and a per-call price of 3¢, which matters for invocation economics. It stops short of describing the shape of a successful result, though the simple schema limits how much that costs.

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, front-loaded sentences: what it returns, when it returns nothing, and where to read more, plus pricing. No filler, and the most decision-relevant content leads.

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 one-parameter read-only lookup with full annotations, most of the burden is on explaining the lone identifier, which the description does not do. Coverage scope, failure conditions and cost are well handled, but an agent still cannot confidently construct a call without knowing what a gnaf_id is.

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 description says 'this address', which hints that the parameter identifies an address, but schema description coverage is 0%. The single parameter is gnaf_id, and nothing in the description explains that it is a G-NAF address identifier or where to obtain one (e.g. via geocode_address); that gap matters because an arbitrary string will simply return not-found. The API documentation link is the only fallback.

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 resource ('government schools this address is zoned for') with sub-scope (primary, secondary) and coverage (current catchment maps for every state and territory). The 'zoned for' phrasing implicitly separates it from nearby/ranking siblings, but no sibling is named explicitly, so the differentiation is left to inference.

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 negative condition ('Not found when the address is unknown or sits inside no catchment we hold') tells the agent when the tool will produce nothing, which is useful. There is no positive when-to-use guidance versus alternatives such as properties_schools_all, properties_schools_nearby or suburbs_schools_catchment, so the agent must infer the routing itself.

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