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

Annotations already cover idempotency and open-world/destructive flags, and the description adds real behavioral context beyond them: nothing prints or mails until payment confirms, an existing open order is reopened rather than duplicated, and a 422 address_incomplete error requires fixing the draft first. It also tells the agent to reuse the same key and arguments on retry, which reinforces the idempotentHint with actionable guidance.

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?

The purpose and precondition are front-loaded in the first sentence, and each following sentence adds concrete value (payment gating, error handling, dedup, retry). Sentences are dense and long, but nothing is clearly 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?

Despite no output schema, the description explains the return value (checkout_url plus a short summary), the approval mechanism, the failure mode (422 address_incomplete with remediation), and retry semantics. An agent has everything needed to call this correctly.

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?

With 0% schema description coverage, the description compensates well: 'this exact saved draft version' clarifies draft_id/version, and 'reuse the same key and arguments on retry' explains idempotency_key's role. The mention of total_cents is slightly confusing since it is not an actual parameter, which keeps this from a 5.

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 ('create (or reopen) its unpaid order and return a Stripe Checkout checkout_url') scoped to a saved draft version. The 'Pay-per-letter send' framing and draft/version scoping distinguish it from send_with_credits, checkout, and prepare_checkout without opening their schemas.

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 a clear triggering condition: only after the customer explicitly approves sending this exact draft version, and notes that payment in Checkout is the approval so no sign-in or review is needed. It does not explicitly name sibling alternatives (e.g., send_with_credits) or state when not to use it, keeping it short of a 5.

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