snooze_email

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

With no annotations, the description carries the behavioral disclosure burden. It discloses the key timed behavior and the email_id format, but does not mention whether the email is immediately read/unread, whether the snooze is cancellable, or any side effects beyond the future unread flag.

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 entire description is a single compact sentence with two purposeful clauses: the action+time behavior and the parameter format. No filler.

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 2-parameter tool with an output schema, the description covers purpose, behavior, and parameter formats. It lacks usage guidance and immediate-state details, but is mostly complete for straightforward invocation.

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 0%, so the description compensates for both parameters: until is specified as ISO time, and email_id follows folder:uid with example. This exceeds the bare schema titles, though timezone or example for until is not given.

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 uses a specific verb-resource pair ('延后提醒' – snooze reminder) and adds a concrete behavioral detail (到期重新标记未读 – re-marks as unread when due). It is distinct from any sibling tool, though it is terse and does not explicitly name 'email' as the resource.

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?

No guidance on when to choose snooze_email over siblings like mark_unread or schedule_send. The description only provides format constraints and does not state use cases, prerequisites, or exclusions.

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