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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: principal and interest only, taxes/insurance/escrow/prepayment penalties excluded, each extra payment applied to principal on its payment date, and no currency conversion. It also discloses the derived outputs, notably the 5-year/1-year-sooner minimum-extra calculation, which is non-obvious behavior.

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?

The purpose and usage guidance are front-loaded and the exclusions are crisp, but the second sentence is a long run-on that enumerates every return value in detail even though a full output schema exists — that enumeration is largely redundant and bloats the definition.

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?

For an 8-parameter financial calculator with an output schema, the description covers what is needed: input mode constraint, unit/currency handling, what is excluded from the calculation, and stated assumptions about when extra payments apply. Nothing an agent needs to call it correctly is missing.

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% and the schema already carries ranges, defaults, and the years_left/monthly_payment either-or note, so the baseline is 3. The description reinforces the mutually exclusive constraint ('not both') and frames years_left as 'time left' and monthly_payment as 'principal and interest only (no escrow)', adding marginal interpretive value on top of the schema.

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 and resource: computes how much sooner a fixed-rate mortgage ends with extra monthly, lump sum, or both, from today's balance. It explicitly names the sibling it is not for ('Do not use for the payment on a new loan (use smartfin_calculate_loan_payment)'), so an agent can separate it from the other calculate_* tools without opening a 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 explicit trigger conditions ('Use when someone asks how much sooner or with how much less interest extra payments or a lump sum pay off a mortgage'), explicit exclusions (refinancing, adjustable-rate/interest-only, pay-off-vs-invest), and the input rule 'Give the time left (years_left) or the monthly payment from the statement (monthly_payment), not both.' Nothing is left to inference.

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