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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description still adds substantive behavior: statelessness, no persistence, no transfers, deterministic largest-remainder allocation, integer-cent arithmetic, and debt offsetting. These are outcome-shaping traits an agent could not infer from the schema or 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?

Front-loaded with the core action and constraints, then behavioral limits, then a short practical tip; nearly every clause carries information. The closing 'Use aliases when possible' is slightly vague about which field it targets.

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 pure computation tool with a full output schema, everything needed to call it correctly is present: input bounds, currency restriction, rounding model, and the fact that it neither reads nor writes external state. Return values are correctly left to the output schema.

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?

Nested schema descriptions exist but top-level coverage is reported low, and the description compensates by explaining equal-vs-weighted share semantics, cent-based amounts, participant/expense count bounds, and the exact supported currency set. It stops short of naming individual parameter fields, leaving field-level detail to the schema.

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+resource ('calculate balances and reimbursement suggestions') and immediately bounds it: 2–30 participants, 1–100 expenses, equal or weighted shares. The scope is unmistakable even without siblings to compare against.

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?

Gives clear operating context — stateless, no account access, no data fetching or storage, no money transfer, single currency with no conversion — which tells an agent what cannot be delegated here. It lacks an explicit when-to-use/when-not framing, but with no sibling tools there is little alternative routing to specify.

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