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

Annotations (`destructiveHint=true`, `idempotentHint=false`, `openWorldHint=true`) flag a risky spend, and the description adds context those hints cannot convey: the price is a 5–1000 USDC x402 charge auto-debited from the managed wallet, the card is non-transferable, and the returned `card.status` starts as 'pending' with details appearing only after ~7–10 seconds. It even specifies the polling cadence and endpoint, which is exactly the kind of behavior an agent cannot infer from structured fields.

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?

Purpose is front-loaded in the first line, followed by response behavior, then the geographic constraint and paid-route prerequisite. It is longer than average and occasionally dense, but every block (payment range, polling, U.S.-only, wallet funding) carries information the agent needs, so little is wasted.

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?

With an output schema present, the description does not need to enumerate return fields, yet it still explains the key response states and the async readiness transition. For a paid, non-idempotent ordering tool with a funding prerequisite, nothing an agent needs to call it correctly is missing.

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 100%, so both `amount` and `format` are already fully documented with bounds and enum meanings. The description restates the USDC payment range and the json/html formats without adding syntax or semantics beyond the schema, so baseline 3 applies.

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 ('Order a USA prepaid card') and immediately scopes it geographically and by currency. It explicitly names the contrasting sibling (`GET /order-intl-card`) for the non-U.S. case, so an agent can differentiate without opening either 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 explicit when-to-use conditions (U.S. merchants, USD, own use only) and an explicit when-not with the alternative to use instead (`GET /order-intl-card` for non-U.S./non-USD). It also states the precondition that the managed agent wallet must exist and be funded via get_agent_wallet before calling.

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