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

Beyond the destructive/idempotent annotations, it discloses concrete consequences: omitted optional fields are cleared, original invoice amounts remain untouched, and no payment is initiated. It also states the token-invalidation behavior, which is exactly what an agent needs before committing a destructive change.

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-loaded with the gating requirement, and each subsequent sentence adds a distinct fact (token constraint, field-clearing behavior, no payment, confirmation requirement). Slightly dense phrasing ('Prepare replacing the observed billing/settlement rates...') costs a bit of readability.

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?

With no output schema, the description still covers preconditions, side effects, and what is preserved, which is what matters for a destructive commit tool. It does not indicate what the caller receives back or how to verify the applied rates, a minor remaining gap.

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?

Only one parameter, and the description reinforces the token's provenance ('exact change returned by ... preview') and its expiry semantics, adding value beyond the schema. It does not restate the token's length/format constraints, but those are already in 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 ('Apply only the exact change returned by preview_set_invoice_settlement'), and the title clarifies it is recording invoice exchange/settlement rates. It explicitly distinguishes itself from the sibling preview tool by being the commit step that consumes the preview's output.

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?

Gives an explicit precondition (only after the user confirms the preview), an explicit input constraint ('Accepts its confirmation_token only'), and an explicit exclusion (changed or expired records require a new preview). An agent cannot confuse this with the preview or with clear_invoice_settlement.

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