Penny Rounding

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

Annotations only provide readOnlyHint and openWorldHint, and the description adds substantial behavioral detail: the exact rounding band behavior, the 'free gain' concept, the warning that rounding delta is not revenue, and the advisory to tell users that four cents is not a pricing strategy. This goes well beyond the 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 front-loaded with the core purpose, followed by usage guidance, a key pitfall warning, input recap, and return summary. Though somewhat long, every sentence earns its place by preventing misinterpretation of a genuinely tricky pricing concept.

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 description explicitly lists the returns: the whole band, highest price, free gain in cents, and a verdict. It also explains the rounding mechanics, tax interaction, and the one free move, making the tool self-contained for an agent despite the domain complexity.

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%, so the baseline is 3, but the description adds meaningful semantics: spreadCents is clarified as 'for how far either side to look' with a 1-50 range and default 5, and taxRatePercent's role is contextualized. It does omit the optional 'rule' parameter, but the schema fully documents it.

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 precise verb and resource: 'find every nearby list price that settles to the SAME cash total, and the highest one.' It clearly distinguishes this from simple rounding tools by focusing on the band of identical cash totals and the optimization opportunity.

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 explicitly tells the agent when to use the tool: for 'what price should I charge' and 'can I price to gain from rounding' questions. It also warns against a common mistaken approach, though it does not explicitly name sibling tools as alternatives.

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

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

The description goes well beyond the readOnlyHint and openWorldHint annotations. It discloses that rounding applies only to cash, only to the total, only after tax, and only according to the trailing digit; it also warns that omitting taxRatePercent usually gives the wrong nickel and that the tool reports arithmetic, not legal requirements. This is rich behavioral context that prevents serious misuse.

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 long but appropriately so given the tool's edge cases. It is front-loaded with the core algorithm, uses bullets to isolate the four failure modes, and every remaining section — input format, return values, and legal caveat — earns 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 no output schema present, the description still enumerates the return fields: exact subtotal, tax, exact total, rounded amount due, signed delta, deciding digit, warnings, and disclaimer. Combined with the detailed parameter semantics and the cash/card rule, the description gives an agent everything needed to invoke the tool correctly and frame the result safely.

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?

Although the schema already documents all parameters, the description adds crucial semantics: numbers are read as cents, strings as dollars, non-integer numbers are refused, taxRatePercent is a percentage like 8.25 rather than 0.0825, and tender defaults to cash. The rule parameter is also tied to legal meanings, which materially reduces incorrect invocation.

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 first sentence states a specific operation — settle a transaction under post-penny cash rounding — and gives the exact algorithm: exact subtotal, tax on subtotal, then round the final total to the nearest nickel for cash only. The cash-only emphasis and the four common-misconception bullets clearly distinguish it from related pricing or rounding-analysis tools.

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 is explicit about when to use it: 'Use this for any "what does X round to" or "what do I owe in cash" question' and when not to apply rounding: card, EFT, and gift-card payments should not be rounded. It does not explicitly name price_band or rounding_impact as alternatives, so it stops just short of full sibling-tool routing.

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

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

Beyond the readOnlyHint annotation, the description discloses important behavioral truths: symmetric rounding nets to exactly zero over evenly spread totals, real .99 price lists make the result small but nonzero, the tax rate changes the landed nickel, and always-up is provided only for quantification. It also explains what to report back, which is especially valuable because there is no output schema.

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 well-structured and front-loaded with the core computation and outputs. It is longer than strictly necessary, with some rhetorical flourishes like 'Do not guess' and 'no jurisdiction has adopted it for retail,' but most sentences carry meaningful context about behavior, inputs, or return values.

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 moderately complex tool with no output schema, the description is remarkably complete: it explains when to use it, why the results behave the way they do, how each input works, what the return values are, and how to present the answer. An agent has enough context to invoke this tool correctly and interpret its 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 description coverage is 100%, so the schema already thoroughly documents prices, taxRatePercent, and rule. The description adds little beyond repeating that taxRatePercent matters and rule defaults to symmetric; these facts are already present in the schema. This is the baseline 3 case where the schema carries the parameter-semantics burden.

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 uses a specific verb ('Compute') and resource ('what cash rounding is actually worth across a list of prices'), and immediately lists the concrete outputs: mean delta, up/down/unchanged split, and per-thousand figure. This clearly distinguishes it from siblings like round_cash_total, which is about rounding a single cash total, by emphasizing aggregate analysis across a price list.

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 explicitly says 'Use this whenever someone asks whether rounding costs or earns money' and warns against guessing. It provides strong contextual guidance for when the tool is appropriate, but it does not explicitly name when-not-to-use it or point to an alternative sibling such as round_cash_total for single-transaction rounding.

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