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

Beyond the annotations, it discloses concrete side effects: the invoice records a payment with method credit, the credit's VAT share comes back off, refunds pay the customer with date and method, and void reverses an erroneous prepayment. It also states the per-call cost and that failures are free, with no annotation contradiction.

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 main allocation behavior is front-loaded, and every clause carries operational meaning despite the dense single sentence. It could be more scannable, but there is little filler and the cost note is appropriately separate.

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 output schema, the description covers the main modes, defaults, constraints, side effects, and cost. It is not fully complete because it does not explain the reference parameter or clarify partial-allocation return 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?

With only 38% schema description coverage, the description compensates well by explaining credit as a prepayment/overpayment, the invoice_id target, the amount default of the smaller remaining credit/invoice balance, and the refund and void flags. It still leaves the reference parameter unexplained and does not add meaning beyond the enum for method.

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: "Put a customer's credit ... on one of their sent invoices," and it clearly covers allocate, refund, and void modes. It distinguishes the operation from a plain payment by explaining that the invoice records it as a payment with method credit and reverses the credit's VAT share.

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?

It explicitly describes when to use allocation versus refund: true versus void: true, including the condition that void applies only while none of the prepayment is used. It also states the same-customer and same-currency constraint, giving clear boundaries for correct use.

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