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

Annotations already declare write, non-idempotent, destructive and open-world behavior, so the bar is lower, and the description adds real context: the tool returns a secure checkout link rather than charging directly, and dry_run previews price and terms. It does not explain what makes the operation destructive or how the flagged-repeat flow (confirm_repeat) works, so it is strong but not complete.

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?

Two tight sentences that lead with the core action and end with the dry_run preview, with essentially no wasted words for an 11-parameter tool. The second sentence is dense enough that a turn or short set of bullets would aid scanning, keeping it just short of ideal.

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 an 11-parameter, nested-object tool with no output schema and multiple payment/routing branches, the description covers the main flow and return artifact but omits several behavioral branches (saved-card payment, repeat confirmation, return-address handling) that an agent needs to call it correctly. It is adequate but with clear gaps.

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 only 55%, so the description needs to compensate, and it does explain dry_run and the recipient_email vs send_to_me routing paths. However it says nothing about pay_with_saved_card, confirm_repeat, sender_address, recipient_label or use_saved_return_address, and gives no format guidance for destination_address, leaving several parameters undocumented in both places.

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 ('Mails a printed copy of a card') and ties it to the sibling choose_card as the source of the card, so an agent knows the ordering dependency. It also names the three destinations (recipient, user, email-provided address) and the return artifact (checkout link), which separates it from siblings like update_card_details, find_cards and get_order_status.

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 implies when to use dry_run ('returns the price and terms first') and how the three routing modes differ, which is useful. But it names no exclusions and does not compare against alternatives like pay_with_saved_card (only documented in the schema) or get_order_status/list_my_orders, so the routing decision is left partly to inference.

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