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

Annotations already flag destructiveHint=true and idempotentHint=true, so the safety profile is set; the description adds genuinely new behavior: the trash is restorable for 30 days, tokens expire or invalidate on record change, and already-pushed accounting outcomes must be reviewed elsewhere. It stops short of saying what a successful call returns or how to verify the result, which keeps it at 4.

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?

Compact overall, but the purpose sentence ('Prepare moving one invoice…') is buried after the procedural constraint, so it is not front-loaded. The trailing 'Requires confirmation' restates the confirmation rule already given in the first sentence, a minor redundancy.

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 destructive tool with no output schema, the description covers the full flow: preview, user confirmation, token validity, and the escape hatch for uncertain accounting states. Naming the restore path or the post-trash verification step would make it complete, but nothing essential is missing.

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 description adds meaning beyond the schema's own note by tying the token to a prior preview and declaring that stale tokens are rejected. That is real semantic value (expiry/invalidations) rather than a restatement of the token field.

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 and resource (move one invoice to trash) and scopes the effect precisely: '30-day restorable trash'. Combined with the token-only constraint, an agent can distinguish it from preview_trash_invoice and restore_invoice without opening any 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?

Gives explicit preconditions ('only after the user confirms that preview'), the accepted input ('confirmation_token only'), and the exclusion path ('changed or expired records require a new preview'), plus a hard stop for pushed/uncertain invoices that must be handled on the website. This is when/when-not guidance, not inference.

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