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

Goes well beyond the annotations: it clarifies that no charge is ever made and no payment is completed, that a human must finish payment on Stripe's hosted page, that the agent must not report the order as paid, and it specifies auth requirements (OAuth or Bearer agent API key) and named error conditions. This is exactly the kind of side-effect and precondition disclosure annotations cannot carry. The destructiveHint=true annotation is conservative but not contradicted, since creating a link mutates nothing the description claims is safe.

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?

Front-loads what the tool does, then the critical caveat that it never charges, then preconditions and auth. No sentence is filler; each one changes agent behavior (don't claim paid, don't attempt payment, expect specific errors).

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?

With an output schema present, the description need not explain the return payload, and it covers everything else an agent needs: eligibility, failure codes, auth, and a behavioral instruction about post-call messaging. Nothing material is missing for correct invocation.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents orderId as the uuid of a dispatched, not-yet-paid order. The description restates the same constraint ("dispatched, not-yet-paid order") without adding format or sourcing detail beyond the schema, matching the baseline of 3.

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+resource+output ("Creates and returns a Stripe-hosted checkout URL") scoped to a DISPATCHED, not-yet-paid order and acting on behalf of the buyer. This is clearly distinguishable from siblings like orders.place, orders.status, and orders.reject, which all concern order lifecycle rather than payment links.

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 clear preconditions for use (order must be dispatched and unpaid) and explicit failure modes (not_ready_for_payment, already_paid) that tell the agent when the tool will not work. It stops short of naming sibling tools as alternatives (e.g., checking state via orders.status first), so it is clear context but not a full when/when-not/alternative map.

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