snooze_email

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

Annotations only include destructiveHint: false, which the description does not contradict. Beyond that, the description discloses a major behavioral trait: the wake is not reliable if the server stops, which is not inferable from annotations. However, it does not detail the cancellation mechanism's side effects (e.g., whether email wakes immediately), but given the explicit warning, it adds significant value.

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 description is a single, well-structured paragraph with a strong imperative verb and correct placement of the critical warning. It avoids fluff and is concise, though the long warning sentence could be split for readability, but this does not detract from substance.

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?

Given the tool mutates an email's location and has a time-dependent behavior, the description fully covers the essential context: what happens on move, when it returns, the fragility of the timer, and the cancellation path. The lack of an output schema is acceptable as the description clarifies state changes, and the sibling tools like cancel_snooze are logically referenced. Minor omission: it does not state whether the original folder is restored exactly, but the operation is clear enough.

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 descriptions cover 100% of parameters, providing clear definitions for emailId and wakeAt. The description adds no extra parameter details beyond what the schema provides, such as example formats or constraints, but since the schema already covers them, a baseline 3 is appropriate.

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 clearly states the action ('Move an email out of sight into Folders/MCP-Snoozed') and the mechanism for returning it ('bring it back to its original folder at wakeAt'). It uses specific verbs and resources, and distinguishes itself from suffixed siblings like 'cancel_snooze' and 'list_snoozed'.

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?

The description explicitly emphasizes the critical scheduling constraint ('wake only fires while this MCP server process stays running') and warns about the fallback behavior if the app closes. It also mentions cancellation via 'cancel_snooze', providing clear when-to-use and when-not-to-use guidance.

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