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

Beyond the annotations it discloses that the tool only hands back a link and performs no payment action, and adds real business semantics (cancellation applies at period end; card-adding is limited to card-less trials). It does not mention link expiry or the fact that each call yields a distinct, non-idempotent link. No contradiction with readOnlyHint=true: the tool itself reads/constructs a URL while destructiveHint refers to the action the link enables.

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 with the action list and the safety directive front-loaded; nothing is filler. The opening noun phrase 'An address at Stripe for the person to open' is a slightly awkward construction for what is really a URL generator, costing a bit of immediate comprehension.

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 simple 2-parameter tool with no output schema, the key gaps are the unexplained 'site' parameter and the absence of any statement about the returned value's form or lifetime. The core intent and the safety rule are covered, so it is adequate but not complete.

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%, so the description must carry the load. It does well on 'action', explaining the intent behind each enum value and the conditions under which each applies. However, 'site' — a required string parameter — is never explained (whether it is an ID, slug, or domain), leaving half the parameters undocumented in both schema and description.

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?

The description makes clear the tool produces a Stripe address (link) the customer opens for one of three billing actions, and enumerates those actions. It is slightly indirect by describing the output as 'an address at Stripe' rather than stating a verb like 'generate a billing link', and it never names the closest sibling (start_checkout), but the resource and output are identifiable.

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 gives explicit when-to guidance per action — 'cancel (at the end of the period)' and 'add_card for a trial that has no card' — plus a hard behavioral rule: hand the address to the person and never act on payment yourself. It does not compare against start_checkout or explain when this link is preferable to a hosted checkout.

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