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

Annotations already guarantee read-only, idempotent, non-destructive behavior, so the description need only add domain behavior — and it does: bracket-by-bracket computation from official schedules, jurisdiction-specific rules (Toronto's double municipal MLTT, AB/SK charging none), rebate inclusion, and a market-price fallback. It does not say how stale the reference prices are or what the output breakdown looks like, which keeps it short of a 5.

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 trigger and the core computation, then a coverage list. The jurisdiction enumeration is long but each item carries real selection value (it tells the agent whether the answer will be trustworthy for a given city), so the length is largely earned rather than padding.

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 three-parameter, no-output-schema calculator with a full annotation set, the description supplies the missing dimension structured fields cannot: jurisdictional coverage, the no-tax provinces, and rebate handling. Only the shape of the returned tax breakdown is unaddressed, which is minor.

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 coverage is 100%, so all three parameters are already documented, including that province is required when ville is absent. The description restates the either/or input pattern ('Give a price, or just a city') but adds no syntax, format, or default-value detail beyond the schema, which is the correct baseline-3 outcome.

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 land-transfer tax') and anchors it to a concrete user intent ('when the user wants to know the land-transfer tax on a home purchase'). The coverage list and the 'Not covered: PEI and Newfoundland' limit make it unambiguous versus the unrelated sibling tools.

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?

Opens with an explicit trigger ('Call this when the user wants to know…'), states the two acceptable input modes (a price, or just a city), and names the jurisdictions it does not handle. When-not conditions are explicit, which is unusually strong for a tax calculator.

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