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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds real behavioral content: the 2026 default, the 5,000 km tier boundary, the province-vs-territory split, and the fact that calculation only happens if kilometres is supplied. It doesn't disclose whether the source is cached or versioned beyond the as-of date, which keeps it below 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?

Two front-loaded sentences with good density; the purpose and default year come first. The second sentence enumerates return fields that the output schema already covers, so it slightly overspends on that clause.

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?

Given an output schema and full annotation coverage, the description only needed to convey purpose, year options, tier behavior, and calc optionality — and it does all four. An agent can pick this tool and call it correctly with no open questions.

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 the baseline is 3, but the description adds genuine meaning the schema lacks: the 5,000 km tier threshold that makes kilometres behave differently above and below that value, and the province/territory duality behind the single region parameter. The default-year behavior is also restated usefully.

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 states a specific verb and resource — it retrieves CRA reasonable per-kilometre allowance rates for employer-paid vehicle allowances — and names the exact structure of the data (first 5,000 km vs after, provinces vs territories). This clearly separates it from siblings like cra_meal_travel_allowance and gst_hst_rate_by_province without requiring schema inspection.

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?

It establishes context (employer-paid vehicle allowances) and states that 2026 is the default year with 2025 also available, plus that calculation is optional. What's missing is an explicit when-not-to-use pointer, e.g. routing meal/ Travel claims to cra_meal_travel_allowance rather than this tool.

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