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

With no annotations, the description carries the burden well: it discloses default and max window, ordering (newest first), the output shape (one-line summary with timestamps), and an access requirement (Pro keys of the Rail Health Index). It does not state pagination limits, rate limits, or what is returned when nothing occurred in the window.

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?

A single dense sentence that front-loads the scope (all status changes), then window, ordering, output example, currency option, and access tier. The inline example earns its space by showing the exact result shape.

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, and the description still gives a representative record, so an agent knows exactly what it will get. Window bounds, ordering, scoping, and access tier are all covered for a simple 2-parameter, zero-required read tool.

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% and already documents the 1–90 bound, the default of 30, and the ISO 4217 currency code. The description only restates the default window and that currency is optional, adding no format or matching semantics beyond 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 precise verb+resource: every status change (degraded, outage, healthy) of a payment method class, newest first, over `days`. The "change of status" framing distinguishes it in spirit from snapshot siblings like get_rail_health, but that sibling is never named, so the differentiation is left implicit.

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?

Implies the use case (reviewing rail outages/incidents over a recent window) and notes optional currency scoping, but gives no explicit when-not-to-use and does not name get_rail_health or get_fx_events as the alternatives for current state or event timelines.

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