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

Annotations already signal non-read-only and non-idempotent behavior, and the description reinforces and expands on this: every call creates a new unpaid order, the token is a secret, a 403 means the caller's jurisdiction is embargoed, and an optional email also receives the eSIM by mail. This adds valuable behavioral context beyond the structured hints.

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?

Every sentence carries essential information: purpose, return values, safety warnings, parameter constraints, error meaning, and alternatives. The critical non-idempotency warning is front-loaded, and there is no fluff or repetition.

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?

The description covers the full workflow: what to confirm before calling, what the response contains and who receives what, error semantics, top-up usage, and the relevant alternative tool. With an output schema present, the description need not enumerate return fields, making this complete for an agent to invoke correctly.

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 0%, so the description must explain parameters, and it does for most: period_num (1–365 and daily_unlimited only), topup_iccid (with plan_id from list_topups), email (also mails the eSIM), and lang (the order page language). It does not explicitly describe payment_method, though its enum values are self-explanatory.

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 specific verb+resource: 'Create an order for a person to pay.' It clarifies the tool's purpose by describing its outputs (token, checkout_url, order_url) and differentiates it from the sibling purchase_esim, which handles wallet payments.

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 gives explicit usage warnings: confirm the plan and price first, every call creates a new unpaid order, and do not retry while a checkout is open. It also names the alternative for wallet payments ('To pay from a wallet use purchase_esim') and explains the top-up use case via list_topups.

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