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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false, so the safety profile is covered. The description adds genuinely new context: a confirmation token is mandatory, the token is single-use against a specific previewed state, and the invoices themselves are retained rather than deleted — which meaningfully softens what 'destructive' means here.

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 critical constraint — apply only the previewed change, only on confirmation — is front-loaded, and every sentence contributes. There is minor redundancy between 'after the user confirms that preview' and the later 'Requires confirmation'.

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?

A single-parameter mutation with no output schema needs prerequisites, token lifecycle, and effect disclosure; all three are present, including post-action state (invoices retained). Only the awkward 'Prepare marking' wording and absence of any success/failure signal leave a small gap.

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 one parameter at 0% stated schema coverage, the description carries the burden and does: it explains that confirmation_token is the only accepted input and that it must be the exact token from this operation's preview after user confirmation. The lifecycle rule (expired/changed → new preview) adds semantics the schema cannot express.

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 concrete effect — marking selected invoices as distinct rather than duplicates — which maps cleanly onto dismiss_duplicate_group and separates it from restore_duplicate_relationships and the preview sibling. The phrase 'Prepare marking...' is a bit muddled (it reads like preview language rather than an applied write), which keeps it short of 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?

It states explicitly that this tool applies only the exact change from preview_dismiss_duplicate_group, only after user confirmation, and that changed or expired records require a fresh preview. The alternative (call preview first) and the exclusion conditions are both spelled out.

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