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

Beyond the annotations, it discloses the key behavioral fact that the snooze lives in the server's own index and 'nothing on the mail server changes', plus the full confirmation protocol including the exact returned status='confirmation_required' and the action_id/plan_token handshake. This is exactly the layer of detail annotations cannot carry.

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 core behavior is front-loaded in the first sentence, followed by the parameter note and then a clearly labeled CONFIRMATION block. The em-dash aside earns its place as an intuition anchor, though the confirmation sentence is slightly dense.

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 two-parameter mutation with no output schema, the definition covers reversibility, storage location, and the confirmation gate thoroughly. Minor gaps remain, such as what happens when a message is already snoozed or whether snoozing replaces an existing wake-up time.

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 50%: the until parameter is already documented in the schema (including 'Omit to unsnooze'), so the description largely restates it. message_id, the required parameter, has no description in either the schema or the description text. Baseline 3 applies since the schema does most of the work.

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 a specific verb and resource ('Hide a message from the list ... then let it come back') and makes the outcome concrete with the 'deal with this on Monday' framing. It does not explicitly contrast itself with any named sibling, so an agent must infer that mail_list_scheduled or mail_mute_thread are not the right call, which keeps it just under a 5.

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 clearly states the two usage modes: supply until for a future wake-up, or omit it to unsnooze immediately. It also spells out the mandatory follow-up path ('the write happens only after confirm_action'), which routes the agent to the confirm_action sibling. No explicit when-not-to-use case is given, so 4 rather than 5.

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