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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses the precise rounding algorithm by final digit, the after-tax timing, the cash-only scope, and the dollar-string versus integer-cents input convention. It also surfaces the legal caveat that no federal rounding law exists as of September 2026 and state law varies, which is valuable context for a computation tool.

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 key behaviors are front-loaded and the prose is readable, but the WHY DELEGATE THIS section repeats the same points from the first paragraph (cash-only, total not item, after tax) and adds peripheral motivational language about floating-point bugs and direct access. It could be tightened 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?

The input side is very well covered, including rounding rules, tender handling, and legal caveats. However, with no output schema, the description never states what the tool returns, such as whether the result is a dollar-string rounded total, an integer cent value, or a breakdown containing subtotal, tax, and rounded total, so an agent still has to guess at the return contract.

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?

With 75% schema coverage the schema already documents subtotal, tender, and taxRatePercent, and the description adds useful semantics about exact subtotal, after-tax rounding, and cash-only behavior. However, the rule parameter and its enum values (symmetric, always-down, always-up, none) are never explained anywhere, and the rounding-digit rule in the description is not tied to which rule value it describes.

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 opens with a specific operation: settle a transaction by computing tax on the exact subtotal and rounding the final total to the nearest nickel for cash only. It clearly distinguishes cash treatment from card, EFT and gift-card treatment, and states that rounding applies to the total, never per-item, so the tool cannot be confused with a generic rounding utility.

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 gives clear selection criteria: use this for cash totals that need post-tax penny rounding, and it explicitly says card and other electronic tenders are never rounded. It does not name an alternative tool such as rounding_impact, but the cash-only trigger and the caution against common wrong explanations are enough to guide when to invoke it.

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