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

It adds substantial context beyond the annotations: nothing is actually ordered until payment, an unpaid order expires in about 15 minutes, and an identical repeat returns the same order - the last of these explains the idempotentHint rather than merely restating it. The total-mismatch refusal and terms requirement further describe runtime behaviour the agent cannot infer from readOnlyHint/destructiveHint alone.

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 dense sentences, front-loaded with what the tool creates and returns. Every clause carries distinct information - checkout URL, prerequisites, refusal rule, expiry, idempotency - with no filler.

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 mutation tool with no output schema, it still names the key return value and the order lifecycle (unpaid, expires, repeat returns same order). The one gap is not mentioning that payment/order state should subsequently be checked via get_order_status.

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 already 100%, so the baseline is 3. The description still adds real meaning by tying expectedTotalCents to get_quote's totalCents and acceptedTerms to the Terms document at a specific URL, and by framing the refund/refusal guarantee in customer terms.

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?

A specific verb and resource ("Creates an unpaid order") plus a stated return value (a Mollie checkoutUrl) make the tool's function unmistakable. It is clearly distinct from the quote/shop-info siblings, which only supply data rather than creating an order.

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 names the prerequisites (accepted terms, total from get_quote) and the refusal condition (a different current total is rejected), which effectively routes the agent through the quote-then-order flow. It stops short of explicitly pointing at get_order_status for the post-payment step, so it is clear but not fully exhaustive.

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