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

Beyond the annotations, the description discloses crucial behavioral traits: it never charges a payment method, only produces a link, and requires the human buyer to complete payment on Stripe's hosted page. It also provides an explicit guardrail about never telling the user the order is 'paid' after calling, and states the required Authorization header. These details add significant context beyond the simple annotations.

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?

Every sentence in the description carries essential information: the core action, the non-charging behavior, the buyer obligation, the post-call communication rule, the failure modes, and the auth requirement. The main action is front-loaded, and the structure flows logically from what it does to how to handle the result, with no wasted filler.

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?

The description is complete for a payment-link tool with one parameter. It covers what the tool does, the preconditions, the failure reasons, the auth requirements, and the important caveat about not claiming payment completion. The output schema exists but is not shown, so the description's mention of returning a Stripe-hosted URL sufficiently communicates the return value.

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 100% schema coverage, the orderId parameter is already documented as 'the uuid of the dispatched, not-yet-paid order.' The description reinforces these preconditions and adds context by explaining the buyer-centric purpose, which helps the agent understand the state requirements for the parameter beyond the schema alone.

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 verb and resource: 'Creates and returns a Stripe-hosted checkout URL' for a 'DISPATCHED, not-yet-paid order'. It clearly scopes the action and differentiates it from payment execution by emphasizing it never charges or completes payment, making it distinct from other order/payment related tools.

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 explicitly specifies when to use the tool: for dispatched, not-yet-paid orders on behalf of the buyer. It also defines when not to use it by documenting failure modes: not_ready_for_payment if not yet dispatched, and already_paid if already paid. This gives clear when/when-not conditions, even if it doesn't name an alternative tool.

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