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

Annotations already declare readOnly, idempotent, non-destructive, non-open-world, so the bar is lower. The description adds real context beyond them: what the call returns (URL, price, live protocols), that the actual payment and drive-queueing occur on a POST to that URL, VAT inclusiveness, receipts on every payment, and that test_mode:true means Stripe test mode with no real money moving. The dense phrasing makes this hard to extract, but the substance is there.

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 ~200-word run-on paragraph of semicolon-chained clauses and protocol jargon (MPP, x402, WWW-Authenticate, PAYMENT-REQUIRED). The most important fact - what the tool returns and that it does not itself charge - is not front-loaded, and large stretches describe the external payment endpoint rather than this tool.

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?

There is no output schema, so the description must carry the return contract, and it does: payment URL, price, active protocols, plus VAT, receipts, buyer/invoice behavior, and test_mode semantics. Coverage of the tool's own effect and edge cases is broad, though the organization makes it less usable than the content warrants.

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?

Only one parameter exists and schema coverage is 100%, so the schema already documents order_id; the description merely repeats 'from order or my_orders'. It additionally mentions a buyer {vat_id, company, address} JSON body, which is not an input-schema property and could be mistaken for a tool argument. That is roughly baseline value with mild added confusion.

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 does convey the resource and situation (an order awaiting payment) and eventually states the actual effect: 'It gives the payment URL, the price and the protocols on now.' But the true function is buried under paragraphs of rail/protocol narration, and the title 'Pay for an order' misleadingly suggests the tool itself pays, when the description shows payment happens on a later POST to the returned URL. An agent must read carefully to learn it is really a payment-instructions lookup.

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?

It scopes the tool to orders 'that waits for payment' and points to where order_id comes from (order or my_orders), which gives implied usage. It also notes account-type conditions (a person's account supports card checkout; an agent's own account has none until claimed). However, it never contrasts with near-name siblings like pay_check, pay_code, or top_up, so the agent gets no explicit routing guidance.

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