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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the risk profile is covered externally. The description adds one genuinely useful piece of context — that an MCP confirmation step is involved — but says nothing about what the refund/cancel_reissue path actually does (e.g. whether a new purchase is created, whether refunds are full or partial, whether they are reversible).

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?

A single front-loaded sentence with no filler and the action list placed first. It is efficiently written, though the terseness is arguably a symptom of under-specification rather than disciplined concision for a 10-parameter destructive tool.

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 destructive, open-world mutation with 10 parameters, 5 required, zero schema descriptions and no output schema, the description is far too thin. It never explains the required idempotency_key, the relationship between kind and action, what lines accomplish, or what a successful response looks like, leaving the agent to guess on a high-stakes operation.

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% across 10 parameters, so the description carries the full explanatory burden and largely fails it. The enumerated verbs loosely hint at the `action` enum values, but the critical ambiguity between `kind` (refund/pre_fulfilment_cancellation/withdrawal) and `action` (refund/cancel_reissue/release_hold) — both of which contain 'refund' — is left entirely unexplained, as are `lines`, `cancel_plan`, `include_shipping` and `withdrawal_request`.

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 names a specific resource (Stripe Checkout purchase) and enumerates the concrete operations (refund, EU withdrawal, release hold, cancel/reissue), so an agent can immediately tell what class of mutation this is. It does not explicitly distinguish itself from stripe_checkout_purchases_get, though the update-vs-get naming makes the split obvious.

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?

There is no guidance on when to choose this tool versus stripe_checkout_purchases_get or the checkout_* siblings, and no prerequisites or preconditions are stated. The only contextual hint is 'MCP confirmation,' which is a behavior note rather than usage routing.

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