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

The annotation readOnlyHint=true and idempotentHint=true already establish the safe, read-only nature. The description adds a crucial behavioral detail: 'Null when the payment can't cover the first month's interest.' This goes beyond the annotations by disclosing a failure condition and the output's null state, which helps the agent interpret results correctly. No contradiction with annotations.

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 description is a single, front-loaded sentence that efficiently states the core calculation, the interest component, and the null condition. Every clause earns its place with no filler, making it easily scannable for an agent.

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 a simple calculator with only three parameters and an output schema (not shown), the description covers the essential semantics: the primary output (months to clear, interest paid) and a key edge case (null when payment insufficient). It does not explicitly state compounding assumptions or formula details, but these are not necessary for selection/invocation. The output schema likely provides return structure, so the description adequately supports correct use.

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% (balance, aprPct, monthlyPayment all have descriptions). The description does not add any parameter-specific semantics beyond what the schema already provides. For example, the schema says 'Fixed monthly payment,' and the description repeats 'fixed monthly payment,' but does not elaborate on units, ranges, or edge cases. Baseline 3 is appropriate when the schema carries the parameter documentation.

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 clearly states the primary function: 'Months to clear a credit-card balance at a fixed monthly payment, plus interest paid.' This identifies the specific computation and the credit-card context, distinguishing it from sibling tools like loan-payoff or debt-payoff. The verb 'clear' combined with the resource 'credit-card balance' leaves no ambiguity about the tool's purpose.

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 offers no explicit guidance on when to use this tool versus alternatives. It does not mention any exclusions, preconditions, or a preferred context. While the credit-card focus is implicit, there is no direct comparison to similar tools like loan-payoff or biweekly-payoff, leaving the agent to infer usage without clear direction.

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