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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real value beyond them: what the call is cryptographically bound to, an explicit no-retry rule on lost responses, and the scope limit that the result is payment state only — not fulfilment or bank settlement. That last clause prevents a very likely agent misinference about downstream order status.

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?

Four short sentences, front-loaded with the action, then the binding constraint, then the failure path, then the result semantics. No filler and nothing repeated from annotations or schema.

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 destructive, 8-required-parameter payment tool with no output schema, the description covers the two things an agent most needs: retry safety and what the result does not mean. It stops short of explaining the channel/mandate_id/cap_each_minor combination, which is the remaining ambiguity in an otherwise complete definition.

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% across 11 parameters, so the description carries the burden and only partially does so. It conveys meaning for order_id, quote_version, price_sha256, approved_cash_minor and the two credential fields, but says nothing about channel enum selection, confirm, idempotency_key, currency, or cap_each_minor — the ones most likely to be guessed wrong.

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 specific verb and resource ("Pay one of the buyer's own orders") plus the two funding mechanisms (Shared Payment Token or signed saved-payment authorization). It also names the sibling it is not — evuun_get_delegated_payment is the read path — so an agent can distinguish it from the other evuun_* payment/commerce tools without opening a schema.

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?

Gives an explicit recovery rule ("On a lost response call evuun_get_delegated_payment; never submit a second payment") and states the binding precondition (exact quote version, price hash, cash amount). It does not, however, advise when to choose channel=spt versus saved_payment_method, leaving the primary branching decision to inference.

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