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

No annotations exist, so the description carries the full burden. It usefully discloses the downstream consequence (client_owned campaigns cannot send or launch if no sender remains), but says nothing about whether the mailbox credentials are preserved, whether the action is reversible via reconnect, or what permissions are required.

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?

Three short sentences: action, consequence, prerequisite. Front-loaded and every sentence carries information an agent cannot get from structured fields.

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?

Covers impact and the approval workflow well for a single-param mutation with no annotations or output schema. The remaining hole is the identifier itself, which neither the schema nor the description explains.

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?

One required parameter with 0% schema description coverage, and the description never mentions mailbox_id — no indication of whether it is the mailbox's own id, a provider address, or a workspace-scoped identifier. With zero schema help, the description had to compensate and does not.

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 action on a specific resource: 'Stop using the mailbox as a sender.' That is clearly distinct from connect_client_mailbox and reconnect_client_mailbox, though the description never literally names the mailbox object being disconnected.

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 an explicit precondition — call only after the user approved preview_disconnect_client_mailbox — which is exactly the kind of gating an agent needs for a destructive action. It stops short of naming alternatives (reconnect, list_client_mailboxes) or conditions where disconnecting is a bad idea.

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