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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds non-obvious behavioral facts on top: the write is token-gated by a prior preview, tokens expire or invalidate when the record changes, and existing notes should be displayed to the user first. These are things the annotations cannot convey.

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 confirmation requirement is front-loaded in the first sentence, but the description restates the same idea three times ('exact change', 'exact supplied text', 'before saving'), so it is somewhat longer than the single-parameter tool requires.

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, no-output-schema commit tool, the description covers the confirmation flow, token lifecycle and the user-facing step well. It stops short of saying what the call returns on success versus a rejected token, which is the main remaining 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?

There is only one parameter, and the nested schema already documents confirmation_token's provenance. The description reinforces the constraint that the token must come from the preview of the exact change and that stale tokens are rejected, but adds little else about format or handling.

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?

States a specific verb ('apply only the exact change') and resource ('an invoice's review notes'), and ties itself to a named sibling, preview_update_invoice_notes. An agent can distinguish this commit step from the preview step without opening either schema.

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?

Explicit routing: call only after the preview has been shown to and confirmed by the user, and only with that preview's token. It also names the exclusion condition — changed or expired records require a new preview — which is exactly the when-not guidance an agent needs.

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