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

Annotations already establish readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description adds methodologically useful context the annotations cannot: the basic personal amount is credited at the lowest rate and the result is pre-Quebec-abatement, which tells the agent what the number actually represents. Reasonable given the annotation floor.

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 purpose and one sentence of methodology, which is good. The enumerated return-field list ('{income_cad, basic_personal_amount, ...}') is largely redundant because an output schema already exists, and it trails off with an ellipsis, so that sentence does not fully earn its place.

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 rich annotations and an output schema, the description need not restate safety or return values, and the calculation rule it does state is helpful. What is missing for correct invocation is routing context — when this federal-only figure is appropriate versus the combined or Quebec calculators — which leaves the definition adequate but incomplete.

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?

There is a single parameter with 100% schema description coverage ('Annual income in Canadian dollars (CAD)'), so the schema carries the semantics on its own. The description adds no further parameter detail (e.g., gross vs. net income, rounding), leaving this at the baseline 3.

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+resource ('Calculate Canadian federal income tax (CRA)') and narrows scope with 'before any Quebec abatement', which lets an agent separate it from provincial tools like calculate_quebec_income_tax. However, it never names calculate_canada_combined_tax or the Quebec calculator as alternatives, so the differentiation is implied rather than explicit.

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?

The description gives no when-to-use guidance: nothing tells the agent when to prefer this over calculate_canada_combined_tax or calculate_quebec_income_tax, nor when a Quebec abatement actually applies. The only pointer ('See list_bundles for related finance-afrique-quebec calculators') is about bundle discovery, not about selecting this tool.

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