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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the read-only/no-network/deterministic statements largely restate structured data. The description does add value beyond them: explicit operational limits (64 KB JSON input, 1 s per call, 1 MB result) and the guarantee that rounded shares still sum to the total charged. It does not clarify what happens when round_up_to forces shares above the total, which leaves one behavioral edge case open.

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?

Structure is excellent: purpose first, then labeled When / Not for / Side effects / Deterministic / Limits sections that are easy to scan. The cost is full bilingual duplication of essentially identical content, which roughly doubles token length for no informational gain.

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?

An output schema exists, so return values need not be described, and the essential routing, safety and limit information is present. The remaining gap is the unresolved edge case of how round_up_to interacts with the 'shares sum to total' promise, which matters for a tool whose whole point is exactness.

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 baseline is 3; the schema already documents total, people, currency, tip_base, round_up_to and tip_percent. The description adds only marginal semantics — that the tip is computed on pre-tax or total (mapping to tip_base) and that rounding applies per share — and never mentions currency or the interaction between round_up_to and the sum-to-total guarantee.

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 (split a bill among people) plus the two defining behaviors: optional tip and per-share rounding that keeps shares summing to the charged total. It explicitly names the sibling it is not (money-allocate), so an agent can route between them without opening either 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?

The 'Cuándo / When' clause names the trigger condition (money, tax or financial-math results that must be exact and reproducible), and the 'No para / Not for' clause names the concrete alternative tool (money-allocate) with the distinguishing criterion (parts must add up exactly). Both use and exclusion are spelled out.

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