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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered structurally. The description reinforces this implicitly by listing clearly destructive actions (delete_label, remove_attachment, disconnect_sender, cancel_domain_order), but adds no explicit statement of irreversibility, permissions, or side effects beyond what the annotations and action names 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 resource scope and the send_email exclusion are front-loaded before the long action enumeration, which is dense but necessary for routing a 22-action dispatcher. The first sentence is a run-on, but nothing is redundant.

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 complex, multi-action tool with a nested 'params' object and no output schema, the description supplies the action list and a help mechanism, which covers discovery adequately. It does not, however, explain return values or per-action effects, leaving meaningful gaps for an operation this broad.

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 description coverage is 83%, so the schema already documents key, draft_id, attachment_id and connection_id. The description's main contribution is directing the agent to call action "help" to discover the fields of the free-form 'params' object, which is modest added value over the schema's own note.

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 the resource scope precisely (threads, labels, settings, forwarding, drafts, held/drafted replies, sending accounts, domain order, owned domain) and enumerates all 22 actions, so an agent knows this is the mailbox mutation dispatcher. It also names the sibling it is not (send_email), which aids differentiation. It stops short of a single crisp verb+resource because the surface is intentionally broad.

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 sending case away from this tool ('Sending is send_email') and points to action "help" for per-action fields, giving a clear entry path. However it does not distinguish against the read-side sibling get_mailbox or indicate which of the 22 mutating actions to prefer in overlapping situations.

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