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

With no annotations, the description carries the full disclosure burden. It reveals major side effects: a receipt email is sent by default, the email goes to a third party, overpayment is recorded with a warning rather than refused, and the email comes from the user's own connection. It does not detail effects on invoice status or failure behavior, keeping it from a 5.

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?

Four sentences, each serving a purpose: core action, email side effect and caution, payment policy, and sender identity. The all-caps warning and the 'money arriving is a fact' phrasing add urgency but are slightly verbose; overall the description is compact and well-organized.

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 an 8-parameter mutation tool with no annotations and no output schema, the description covers the most critical context: the external email contact, confirmation guidance, partial/overpayment behavior, and sender identity. It does not describe the return value or how invoice balance/status is updated, but the risks and preconditions for invoking the tool are sufficiently addressed.

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 coverage is 75%, so the input schema already documents most parameters. The description adds meaning around sendReceipt, tying it to the in-person cash exception, and emphasizes amount confirmation. Other parameters like reference, method, and receivedAt are adequately covered by the schema.

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: 'Record a payment received against an invoice.' It is immediately distinguishable from sibling tools like invoice_payments_list and invoice_payments_reverse because this is the recording action, not list or reversal.

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?

Clear usage context is provided: confirm the amount with the user first because a receipt email contacts a third party, and sendReceipt can be turned off for cash handed over in person. It does not explicitly mention alternatives like invoice_payments_reverse or invoices_send, but the conditions for using this tool are well implied.

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