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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds genuinely new context: the token is single-use-bound to a record state, expiry invalidates it, and financial edits can reset approval. It does not explain what the call returns or how to retrieve the result (relevant given the sibling get_result tool).

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 prerequisite (preview plus confirmation) is front-loaded and the whole text is four short sentences. 'Requires confirmation' slightly repeats the opening sentence, a minor redundancy rather than bloat.

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 mutation with no output schema, the description covers prerequisite, token lifecycle, and the approval side-effect, which is what an agent needs to call it safely. The missing piece is post-call behavior - whether a result must be fetched via get_result - which matters for a destructive financial edit.

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?

Although schema coverage is reported at 0%, the description explains the single parameter's provenance, validity window, and user-confirmation prerequisite, going beyond the schema's wording. It does not clarify token reuse behavior across retries, so it falls short of full coverage.

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: applying the exact change produced by preview_edit_invoice_line_item to a previously read invoice line. It implicitly distinguishes itself from the preview (which prepares) and from sibling mutators like add/remove_invoice_line_item, though a sentence explicitly naming those alternatives would sharpen it. The phrase 'Prepare changes to one previously read invoice line' is slightly confusing for a tool that applies rather than prepares.

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 gives explicit when-to-use and when-not-to-use conditions: call only after the user confirms the preview output, and only with that preview's token. It also states the exclusion case - changed or expired records require a new preview - leaving nothing to inference.

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