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

Annotations already declare readOnly, idempotent, and non-destructive behavior, but the description adds valuable context beyond that: values are in cents, there is no cash-out API, and partial failures are reported inline instead of failing the whole call. This materially informs agent expectations.

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?

Three sentences, each with a distinct purpose: scope, unit conversion warning, and operational constraints. No filler or repetition; the most important scoping claim is front-loaded.

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 simple one-optional-parameter, read-only call with no output schema, the description covers the response categories, unit convention, failure behavior, and an important non-capability. An agent has enough to call it correctly and set user expectations.

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 schema already documents redemption_status as a filter for cash-out history. The description mentions cash-out history and status-relevant sections but does not add new parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate.

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 states a specific verb and resource ('get earnings') and clearly enumerates what the call returns: current balance, pending/locked earnings, and cash-out history. This distinguishes it from money-adjacent siblings like get_referrals or list_invoices by claiming to be the single call for all money questions.

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 opening line 'One call for every money question' gives strong when-to-use guidance, and the explicit 'There is NO API to trigger a cash-out; that is app-only' prevents an agent from attempting an impossible operation. It does not explicitly name alternative tools, but the scope claim is sufficient given the sibling list.

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