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

Annotations already mark this as destructive and non-read-only, and the description adds substantial behavior: the invoice number is burned, open balance drops to 0, the document remains readable and stamped VOID, and payments-applied invoices are blocked. This is richer than what the annotations provide.

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 key action and scope are front-loaded. It is informative but somewhat repetitive, restating effects such as the burned number and readable VOID document in both prose and the final effects line.

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, the description covers the essential effects and constraints an agent needs. It explains what happens to the invoice, the number, the balance, the document, and when voiding is blocked.

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 both parameters are already documented. The description reinforces that the reason is permanent and part of the record, but adds little syntax or format meaning beyond 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?

States a specific verb and resource: "Kill an invoice, on the record." The scope is clear, and the description distinguishes this action from reissuing corrected work as a fresh draft.

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?

Explicitly says when to use it: mistakes and cancellations. It also states a key exclusion - invoices with payments applied cannot be voided at 0.1 - and gives the alternative action of reissuing corrected work as a fresh draft.

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