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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false; the description adds value by disclosing the financial permission requirement, the confirmation-gating requirement, and token expiry semantics, plus the fact that original amounts are retained. It stops short of saying whether the removal is reversible or what the caller sees afterward, so not a 5.

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 sentences, all carrying information, with the confirmation-gating constraint front-loaded. The phrase 'Prepare removing an invoice's operational exchange-rate annotation' is grammatically odd and could be tightened, but there is 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, confirmation-gated mutation with no output schema, the description covers the precondition chain, permission requirement, and token invalidation. It does not describe post-state or error behavior beyond 'requires a new preview', leaving a small gap an agent might want.

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 exists and the description explains its provenance and validity window ('the exact change returned by preview... changed or expired records require a new preview'), which reinforces the schema's own token description with lifecycle semantics. Slight redundancy with the schema keeps it from a 5.

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 action (apply the exact change from the preview) and a specific effect (removes an invoice's operational exchange-rate annotation while retaining original amounts), which distinguishes it from set_invoice_settlement. The wording 'Prepare removing...' is slightly awkward and the tie between the tool name ('settlement') and the described object ('exchange-rate annotation') takes a moment to reconcile, keeping it just below a 5.

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 names the prerequisite (preview_clear_invoice_settlement must be run first), the required user confirmation step, the alternative when stale (changed or expired records require a new preview), and the only accepted input (the confirmation_token). The agent has no ambiguity about when this tool may be invoked versus the preview sibling.

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