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

Annotations already declare readOnlyHint, idempotentHint, and a closed-world nature, so the safety profile is covered. The description does add real domain context — the 18%/$33,810 room formula and the provincial-refund scope — which goes beyond structured fields. It still says nothing about estimation caveats, rounding, or what the response contains, so it is not rich enough for a 4.

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 sentences, with the most decision-relevant fact (the 2026 room formula and cap) front-loaded. The trailing web-page URL is useful for verification but is the one element that does not help an agent invoke the tool. Otherwise zero waste.

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 ten optional, defaulted parameters and no output schema, the description does the necessary work of naming the three result classes (room, refund, growth), so an agent knows what it will get back. Missing are any note that results are estimates and how defaults behave, but the tool's computational nature makes that a minor gap.

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% and each of the ten parameters carries its own domain-specific note (PA as Box 52 of last year's T4, unused room from the CRA notice of assessment, the 71-year conversion limit). The description adds only the $33,810 cap and 18% rate, which lightly reinforces `earned` but does not extend the schema. Baseline 3 is correct when the schema does the heavy lifting.

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 names a specific resource (RRSP) and enumerates the three concrete outputs: contribution room, provincial tax refund from a contribution, and growth to retirement. That is far more than a restatement of the name. It does not explicitly contrast itself with close siblings such as tfsa_calculator or retirement_calculator, so it falls 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 only implied by the domain rule (new 2026 room = 18% of 2025 earned income). There is no statement of when to prefer this over tfsa_calculator, retirement_calculator, or income_tax_calculator, and no prerequisites or exclusions are given. Adequate-but-thin context for a heavily overlapping sibling set.

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