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

Goes well beyond the destructiveHint=true annotation: it discloses that numbers stay gapless, that voided documents can no longer be paid/accepted/viewed, that drafts are discarded, that book-posted invoices are reversed in the ledger, and that the call costs $0.01 but is free on failure. These are exactly the behavioral facts the annotations don't carry.

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?

Front-loads the core action ('Void a document') and then packs refusal conditions, alternatives and pricing into dense but purposeful sentences. Slightly long and clause-heavy, but virtually every sentence carries operationally relevant information.

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?

Given a mutation tool with no output schema, the description covers preconditions, side effects, ledger reversal and cost comprehensively. The only gap is what the call returns on success/failure and no mention of the optional reason parameter's role.

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 50%: invoice_id is documented in the schema, but the 'reason' parameter has no schema description and the description never mentions it. The description does implicitly add value by clarifying that quotes and credit notes also carry an invoice_id, but the reason field remains undocumented in both places.

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 (void) applied to specific resources (quote, invoice, credit note) and describes the different outcome per document state (sent keeps its number, draft discarded). This clearly separates it from siblings such as invoices_create_credit_note or invoices_update.

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 enumerates when the call is refused (payments recorded, invoice with credit notes, credit note, invoice possibly in customer's hands) and names the alternative remedy for each case ('correct those with another credit note or a new invoice', 'cancelled with a credit note for all of it'). An agent can decide when to use this vs. a credit note without inference.

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