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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is partially covered. The description still adds real value by disclosing the token lifecycle, the confirmation requirement, and that the source is not re-read (avoiding stale-preview races). It does not, however, say what a prior flag or note is replaced with, which matters given destructiveHint=true.

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 with noticeable redundancy: "after the user confirms" and "Requires confirmation" restate the same gate, and the actual purpose arrives third. It is not bloated, but ordering and repetition cost it.

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 one-parameter mutation tool with annotations but no output schema, the definition covers the confirmation flow, token expiry, and non-re-read behavior. The remaining gap is the effect on any pre-existing flag or note, which an agent would want before invoking a destructive-flagged 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?

Only one parameter exists, so the baseline is 4, and the description reinforces the constraint "Accepts its confirmation_token only" plus expiry semantics. The schema's own token description is largely duplicated rather than extended, so it stops short of 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?

The description names a specific action and resource: "marking an invoice for attention with an optional explanatory note," which lets an agent distinguish it from siblings like edit_invoice_fields or update_invoice_notes. The purpose statement is buried in the third sentence rather than front-loaded, and the opening sentence describes the confirmation workflow instead of the tool's effect, which slightly muddies first-read clarity.

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 routes the agent to preview_flag_invoice as a prerequisite, states the user-confirmation gate, and covers the failure case ("changed or expired records require a new preview"). With ~90 sibling tools, this is exactly the when/when-not guidance needed.

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