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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: what is bundled into the result (transfer tax + registration fee + total due) and, critically, what is excluded (mortgage registration fee), which prevents misreading the output as an all-in cost.

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 sentences, no filler, with the core scope front-loaded and the exclusions and edge cases trailing in order of importance. Dense but every clause carries information about coverage or output composition.

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?

No output schema exists, and the description compensates by enumerating what the result contains (LTT estimate, registration fee, total due at registration). Combined with the parameter-level coverage notes, an agent has enough to call it and interpret the answer, though exact return field names remain unspecified.

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 80% and the description supplements it meaningfully by mapping parameters to real-world cases: Toronto triggers the municipal MLTT, Montreal uses welcome-tax brackets, and first-time buyer rebates apply. It doesn't spell out the province-by-province fee schedule, but the semantics of each input are clear.

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 (estimate) and resource (land transfer tax on a home purchase), and scopes it precisely: 13 provinces/territories, Toronto MLTT, Montreal welcome tax, first-time buyer rebates, plus registration fee and total due. An agent can distinguish this from siblings like capital_gains_tax or mortgage_payment without opening the 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?

Gives clear usage context and useful exclusions: it explains that AB, SK, NL and the three territories charge only the registration fee, and that the mortgage registration fee is a separate cost not included. It doesn't name a sibling tool as an alternative, but the domain boundaries are unambiguous.

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