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

Beyond readOnlyHint/idempotentHint, the description discloses the non-obvious destructiveness of the eventual change ('Omitted optional fields are cleared'), reassures that original invoice amounts remain unchanged, states no payment is initiated, and explains the token's five-minute expiry. These are exactly the behavioral traits structured fields cannot convey.

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?

Four dense sentences, each contributing new information, with the 'does not apply the change' caveat front-loaded via a negative also appearing early. The opening clause 'Prepare replacing the observed...' is slightly awkward but not wasteful.

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 single-parameter preview tool with annotations covering the safety profile and no output schema, the description supplies the workflow (confirmation token), side effects of omission, and the no-application guarantee. Only failure conditions and what the preview body contains are left unstated, which the confirmation-token framing covers adequately.

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 description coverage is 0%, so the description carries the burden; it names the rate fields and the optional date/note and, importantly, explains that omitting them clears existing values. However, invoice_id and base_currency semantics (currency pairing, UUID requirement) are never addressed, leaving key parameter meaning unstated.

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 action (prepare a preview of replacing billing/settlement rates plus optional date/note on an invoice) and explicitly notes it does not apply the change, which effectively separates it from the mutating sibling set_invoice_settlement. It never names that sibling outright, so the differentiation is implied rather than explicit.

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?

'Requires confirmation' plus returning a five-minute confirmation token makes the intended workflow (preview first, then confirm) clear. It lacks an explicit 'use this instead of set_invoice_settlement when...' statement, but the context is unambiguous.

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