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

With no annotations supplied, the description carries the full burden and does disclose meaningful side effects: payment history is updated and the subscription "will likely revert to it's last state." It is silent on permissions/auth requirements, true reversibility, and failure modes, and the hedge "likely" leaves the subscription outcome uncertain.

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 purpose is correctly front-loaded, but "The system allows unpaid invoices to be deleted" and "Only works on unpaid invoices" restate the same constraint, and the JSDoc tags pad the prose. Tighter phrasing would drop roughly a third of the text without losing information.

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 single-parameter tool with no output schema, the description covers the essentials and usefully mentions the return shape ("a json object, containing the results in the 'values' object"), which the absent output schema would otherwise leave undocumented. Missing items are minor: auth/permission expectations and post-delete error behavior.

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%, so the schema contributes nothing beyond `type: integer`. The description's "@param invoice_id: The database invoice_id" clarifies that this is the internal database identifier rather than an external/customer-facing reference, which is a small but real addition; it gives no format or example.

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 opening line names a specific verb and resource ("Deletes an unpaid invoice") and adds the side effect of updating payment history. No sibling tool performs invoice deletion, but the description never explicitly contrasts itself with the payment/subscription siblings, so it stops short of full differentiation.

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?

"Only works on unpaid invoices" gives one clear precondition/exclusion, which is genuinely useful. However, it names no alternative for the paid-invoice case (e.g., refund or credit workflow) and offers no guidance on when a caller would want to delete versus log a payment.

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