invalidate_payment_link

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

Annotations already mark the operation as destructive, but the description adds crucial context: irreversibility, reference ID uniqueness and non-reusability, lack of status checking, undefined outcome for paid links, non-retry on transient failures, and the raw envelope return. This far exceeds the annotation baseline and fully discloses behavioral nuances.

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?

The description is front-loaded with the core action, then delivers necessary warnings and alternatives without redundant language. Every sentence provides distinct value, and the structure (purpose, consequences, caveats, alternatives, return behavior) is logical and easy to parse.

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, irreversible operation, the description covers all key aspects: irreversible consequences, unique ID constraints, undefined behavior on paid links, alternative tools, and retry behavior. The output schema exists, so return values need no explanation, and the description still manages to mention it returns the raw envelope.

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?

The schema covers the parameter with 100% description, and the tool description reinforces it by explaining that reference IDs are unique and cannot be reused, and that the parameter is the user-set reference ID, not Wayl's internal ID. This adds meaningful semantic context beyond the schema, though the schema already carries the primary definition.

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 opens with a specific verb and resource: 'Cancel a payment link unconditionally so it can no longer be used.' It clearly distinguishes from the sibling `invalidate_payment_link_if_pending` by emphasizing 'unconditionally' and from `create_refund` by noting it cancels the checkout, not the money.

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?

Explicit guidance is provided: 'Prefer `invalidate_payment_link_if_pending`, or confirm with `check_order_paid` first.' It also directs users to `create_refund` if the buyer already paid, and warns that invalidating a paid link yields undefined behavior. This is comprehensive when-to-use and when-not-to-use advice.

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