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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, so the '[write]' prefix adds nothing. The description does add one genuinely non-structured rule (PAID requires confirmed payment, record evidence in note), but it never explains the destructive aspect the annotations flag — whether prior status/state is lost, whether invalid transitions are rejected, or whether the change is 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?

Two tight sentences with the action and its state vocabulary front-loaded and the safety caveat second. No filler, and the parenthetical about note is packed with operational meaning.

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 4-param mutation with no output schema and no schema descriptions, the definition covers the target states, both identifier forms, the note's purpose, and the key business rule. Missing only edge behavior an agent might need: identifier requirement when both are null, and what happens if the invoice cannot legally move to the requested state.

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?

With 0% schema description coverage the description must carry the load, and it does: it supplies the legal values for `status` (the schema lists none), states that `invoice_id` or `invoice_uuid` both identify the target, and explains `note` as the place for payment reference/evidence. It omits the fact that neither identifier is schema-required, so the caller has no explicit cue that at least one must be supplied.

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 (move an invoice's status) and enumerates the exact target states DRAFT | SENT | PAID | OVERDUE | CANCELLED, which no sibling offers. An agent can tell this apart from send_customer_invoice or create_customer_invoice because the outcome is a state transition, not a delivery or creation.

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 an explicit precondition for the risky case: 'Use PAID only when the customer's payment is confirmed (put the reference or what they said in note).' It also tells the caller either identifier form works. It stops short of saying when to prefer this over send_customer_invoice (which presumably also flips state to SENT) or which identifier to prefer when both exist.

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