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

Annotations already flag destructiveHint=true, but the description adds substantial behavior the annotations cannot convey: idempotency ('blocking twice does not stack rules'), non-retroactivity for existing mailbox contents, and the mandatory two-step confirmation flow with status='confirmation_required', action_id, plan_token, and confirm_action. This is exactly the extra context an agent needs before calling.

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?

Four short sentences, front-loaded with the effect, then the idempotency and non-retroactivity caveats, then the confirmation contract in capitals. No filler or 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 destructive two-parameter tool with no output schema, the definition covers the effect, the side effects on existing mail, repeat-call behavior, and the exact return status an agent must handle. Nothing material is left to inference.

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 100% and the schema already explains both the bare-address/From-header option and the message_id alternative. The description's phrase 'from an address' adds only marginal meaning and does not explain the either-or relationship, so the baseline 3 applies.

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 ('Stop hearing from an address') and discloses the mechanism: future mail is classified as spam and routed to Trash by a rule. That mechanism distinguishes it from softer siblings like mail_mute_thread without needing to name them.

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 clear when-to-use context plus an important limitation ('Mail already in the mailbox is not touched; move it yourself'), effectively steering the agent to mail_move for cleanup. It stops short of explicitly naming an alternative such as muting a thread, so it is clear but not fully comparative.

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