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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's job is to add computation semantics — which it does: half-year rule, AIIP, post-2024 accelerated incentive keyed to acquisition date, and a 5-year schedule. It also flags the non-obvious rule that CCA can't create a rental loss. It stops short of stating assumptions or rounding/interpretation caveats.

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?

A single dense sentence, front-loaded with the resource and scoping terms, with no filler. It is long and clause-heavy but every clause names a distinct computed output, so little could be cut without losing information.

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 10 parameters (1 required), no output schema, and only a single-sentence description, the enumeration of returned figures (rate, year-1 CCA, tax saving, 5-year schedule, recapture/terminal loss) effectively substitutes for a missing return-value spec. What remains thin is the relationship between optional inputs (existingUCC, disposal fields) and the outputs, but the core is complete for a pure calculator.

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 carries per-parameter meaning and the baseline is 3. The description adds only marginal value — the note that acquisition date selects the half-year/AIIP/accelerated treatment, and the rental-loss cap on netRentalIncomeBeforeCCA — without explaining how existingUCC or disposalProceeds feed the schedule.

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 resource (CRA capital cost allowance on a business or rental asset) and enumerates exactly what it computes: class rate, year-1 CCA with half-year rule/AIIP/accelerated incentive, tax saving, 5-year schedule, recapture/terminal loss. This makes it clearly distinct from siblings like income_tax or capital_gains_tax 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?

Usage is implied by the domain ('business or rental asset', CRA), and the output list hints at when an agent would want it. However, there is no explicit when-to-use statement and no routing to or away from alternatives such as capital_gains_tax or income_tax, leaving the agent to infer the boundary.

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