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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the rate provenance ("Rates as on payotte.com/australia") and the return behavior ("warnings list every assumption and any upper-limit figure"), which tells the agent the result carries caveats rather than a bare number.

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?

Front-loaded with the jurisdiction marker and the core verb, then the option list and finally the source/warning note. It is dense and slightly run-on (the parenthetical SA aside interrupts the state list), but every clause carries operational information and nothing is padded.

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 does the work of signalling what comes back: a duty figure plus warnings enumerating assumptions and upper-limit figures. Combined with the 100%-covered input schema and safety annotations, an agent has enough to call it correctly; only a concrete note on pagination or response shape is absent, which is not relevant here.

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?

Schema description coverage is 100%, so the schema already documents price, state, and each eligibility flag; baseline is 3. The description groups the options into a scenario ("first home buyer, principal residence, foreign buyer (surcharge and FIRB fee) and new home options"), which adds modest framing, but it introduces a small mismatch by citing "land titles registration fees" while the actual parameter is include_mortgage_registration.

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 and resource ("Computes the duty on buying a home") and scopes it to Australia with a per-state/territory breakdown. It goes further than siblings like stamp_duty_in or purchase_tax_uk by naming the supported jurisdictions (NSW, VIC, QLD, WA, TAS, ACT, NT) and explicitly excluding SA with a reason, so an agent can route without opening any 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 description makes the usage context clear: buying a residential home in Australia, with an explicit coverage exclusion (SA not supported). It does not name alternative tools to use instead when SA or non-AU jurisdictions are the target, so the routing is implied by the "AUSTRALIA." prefix and state list rather than stated as when/when-not guidance.

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