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

Beyond the readOnly/openWorld annotations, it reveals substantive behavior: symmetric rounding nets to zero by construction, always-up is worth about 2 cents/sale, rounding applies post-tax to totals in cash, and floating-point money is risky. It stops short of describing the output shape, but adds real context.

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 main purpose is front-loaded and the WHY DELEGATE section is organized around the four key misconceptions. The ownership URL and aggregator note are slightly extraneous, but they do not obscure the core guidance.

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 no output schema, the return value is never specified, and parameters like taxRatePercent lack precise semantics. The conceptual model is strong, but an agent would still have to guess at some invocation details and how to interpret the result.

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 only 33%, so the description must compensate. It gives meaning to rule (symmetric vs always-up) and connects taxRatePercent to the 'after tax' behavior, but it leaves taxRatePercent units and the always-down/none cases undocumented.

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 verb and resource: 'Compute the mean rounding delta per cash transaction across a price list.' It also frames the business question it answers, but it does not explicitly differentiate itself from the sibling round_cash_total.

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 a clear use case—quantifying whether rounding makes retailers money, with the always-up option as an example. However, it never states when to use this tool versus alternatives like round_cash_total, or any exclusion conditions.

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