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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds useful behavior beyond annotations: the confirmation-token expiry condition and the side effect that clearing a whole-invoice tag retains all line allocations. It does not discuss permissions or whether the operation can be undone, but the key mutation behavior is disclosed.

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 core instruction is front-loaded and the description is short. Some sentences are slightly redundant or awkwardly ordered, such as repeating the confirmation requirement after already saying 'after the user confirms that preview,' and the phrase 'Prepare clearing...' reads as a leftover fragment.

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, single-parameter, no-output-schema mutation, the description covers the critical workflow: preview first, confirm, apply exact change, token expiry. Destructive hint already covers risk, and the retention behavior is an important extra. It could mention irreversibility more directly, but it is otherwise complete enough to call correctly.

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?

There is only one parameter, and the schema itself documents confirmation_token as the exact token from the preview. The description adds that only that token is accepted and that changed or expired records require a new preview, which gives meaningful operational semantics beyond the schema. It does not add format details, but little more is needed for a single confirmation token.

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: apply the exact change returned by preview_clear_invoice_load. It also names the resource scope (whole-invoice or printed-line allocation) and distinguishes the operation from its preview sibling. An agent can tell this is the execution step after preview, not the preview itself.

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?

It explicitly says to apply only after the user confirms the preview and to accept only the confirmation_token. It also states that changed or expired records require a new preview, which is a clear when-to-use/when-not-to-use rule. No alternative execution path is left ambiguous.

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