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

Annotations already disclose the open-world, non-read-only, non-idempotent, non-destructive profile, so the description does not have to restate safety. Instead it adds real behavioral value: the tool returns an address that must be handed to the person, the card is entered there, the trial begins, and the first real charge lands after the trial. It does not say what happens if it is called twice for the same site, which matters given idempotentHint=false.

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 carry only load-bearing information about outcome, user action, billing timing, and the next tool call. The opening phrase 'Stripe's checkout for a site create_site reserved' is over-compressed to the point that it needs a second read, so the purpose is not perfectly front-loaded.

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?

There is no output schema, so the description must carry the return value, and it does by explaining that an address comes back and must be given to the person. For a three-parameter billing-flow tool, the agent knows what to pass, what to do with the result, and which tool to call next. What it does not explain is repeated-invocation behavior, such as whether a second call opens another checkout session.

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 33%: only interval is documented in the schema, with the month-or-year and cheaper-yearly note. The description adds some meaning by tying plan to 'the plan the person chose' and site to the site create_site reserved, but it never explains whether site takes an id or a handle, nor what the seven plan values mean or where to get them. Adequate but it does not fully compensate for the coverage gap.

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 states a specific action: it opens a Stripe-hosted checkout page for a site that create_site already reserved, on the chosen plan. That is a clear verb-plus-resource definition that an agent can map to the input schema. It loses a top score only because the framing sentence is grammatically tangled and it never distinguishes the tool from the sibling billing_link.

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?

The description places the tool in a sequence: it comes after create_site has reserved the site, and it must be followed by site_status. That is clear when-to-use context. It gives no exclusions and never contrasts with billing_link or start_setup, so the guidance is contextual rather than a full decision rule.

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