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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the confirmation requirement, that it does not re-read the source, that the return is an exact preview plus a five-minute confirmation token, and that the change is not applied. The token's expiry window and the no-mutation guarantee are exactly the behavioral facts an agent needs and cannot get from annotations.

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?

Three short sentences, front-loaded with the action, then the confirmation prerequisite, then the return contract. No redundant restatement of the title or annotations.

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?

No output schema exists, and the description covers the return value anyway (exact preview plus a five-minute token). It also states the non-applying, non-refetching semantics, which is everything needed for a correctness-critical single-parameter preview tool.

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?

With 0% schema description coverage on a nested object, the description must compensate: it conveys both fields semantically ('an invoice' for invoice_id and 'optional explanatory note' for notes, confirming optionality). It does not mention the UUID format or the 10000-character cap, so it does not fully close the gap.

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 uses a concrete verb+resource: 'Prepare marking an invoice for attention with an optional explanatory note', and the preview framing ('does not apply the change') lets an agent distinguish it from a state-changing sibling. It never names flag_invoice as the applying counterpart, so the sibling pairing 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' and 'it does not apply the change' imply the preview-then-apply flow, which is the intended usage context. However, no alternative tool is named and there is no explicit statement of when to skip this preview and call the applying tool directly.

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