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

Goes well beyond the destructiveHint annotation: it discloses the state transition (paid invoice returns to sent), that no money moves (no refund implications), and the confirm/preview behavior. Rich behavioral context for a mutation.

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?

Three tight clauses front-load the core action and consequence, then the confirm requirement. Every sentence earns its place with no filler.

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 mutation with no output schema, it covers the effect, the state change, the no-money-movement clarification, and the safety gate. An agent has everything needed to call it correctly.

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 100%, so the schema already documents both paymentId and the confirm preview semantics. The description restates the confirm behavior but adds no syntax or meaning beyond the schema, so baseline 3 is correct.

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?

Specific verb+resource: "Deletes a recorded payment from an invoice," and it clarifies the scope (reverses a bookkeeping note, not a money movement). This clearly distinguishes it from record_invoice_payment, void_invoice, and delete_expense.

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?

Explains the scenario (undoing a recorded payment so a paid invoice reverts to sent) and the confirm:true requirement. It stops short of naming an explicit alternative tool for a related need, but the usage context is clear.

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