Preview a reversible batch

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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers on genuinely new behavior: a 500-message cap, a 15-minute plan TTL, all-or-nothing validation, single-account scope for moves, 7-day local history/undo retention, and the guarantee that message bodies never enter the journal. These are operational traits no annotation or schema field conveys.

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 identity and the no-side-effect guarantee are front-loaded in the first sentence, and every subsequent sentence adds a distinct constraint. The middle section stacks three unrelated concerns (target validations, TTL/undo retention, and the changes alias rule) into a dense block, costing some readability.

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?

With an output schema present, return values need no explanation, and the description covers TTL, atomic failure, retention, and the parameter aliasing trap. The remaining gap is the action/destination coupling for moves, which an agent could get wrong on a first call.

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?

Schema coverage is 0%, so the description must carry the burden, and it does the highest-value part: it enumerates which keys `changes` accepts and warns that the top-level read/flagged/add_tags/remove_tags fields are aliases that must not be combined with a changes object. It leaves `action`, `message_ids`, and the requirement that `destination_folder_id` be supplied for a move undocumented, so the mark/move discriminator stays implicit.

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 opening sentence gives a specific verb and resource ('Preview changes to up to 500 messages without changing mail'), which immediately separates it from the single-message mutation siblings like mail_mark and mail_move. It never names mail_batch_apply, the sibling it pairs with, so the preview-vs-apply distinction is inferred from 'without changing mail' rather than stated.

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?

'Any invalid message prevents applying the plan' and the 15-minute plan expiry make the intended workflow (preview now, apply later) clear without spelling out the alternative tool. There is no explicit when-not guidance or named successor, so the agent must infer that mail_batch_apply consumes the plan.

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