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

Beyond the annotations (idempotent, non-destructive, non-readonly), the description discloses the state transition semantics — null reverts to a draft — and the validation contract: times are interpreted in the event's timezone and datetimes carrying a timezone designator are rejected. That rejection rule is the kind of surprise failure mode an agent otherwise only discovers at call time.

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 sentences, each doing distinct work: purpose, per-value behavior, and timezone/format rule. The safety-critical format constraint is stated up front rather than buried, and there is no restatement of the title or schema boilerplate.

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?

With an output schema present, the description needn't explain return values, and the annotations carry the safety profile. The remaining things an agent needs — what the tool mutates, how null behaves, and the exact datetime format accepted — are all present, leaving no material gap for a 3-parameter call.

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 100%, so the baseline would be 3, and the schema already documents scheduled_at's format and null meaning. The description nonetheless adds the enforcement detail — tz-designated datetimes are rejected, only naked local times are accepted — which sharpens the accepted syntax beyond the schema's example.

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 opens with a specific verb set ("Set, change, or remove") applied to a precise resource ("a notification's scheduled delivery time"), so the mutation and its target are unambiguous. The resource qualifier (notification vs. poll vs. survey) also separates it from siblings like update_poll_schedule and update_survey_schedule without needing their schemas.

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 gives explicit conditions for each branch: a future datetime schedules a draft or reschedules an existing schedule, and null removes the schedule and reverts to a draft — this is real when-to-use guidance keyed to parameter values. What it doesn't do is name an alternative tool (e.g., publish_draft_notification, create_notification) for the case where the caller actually wants to send now rather than schedule.

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