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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true, openWorld=false), so the bar is lower. The description still adds real behavioral context beyond them: times are interpreted in the event's timezone and timezone-carrying datetimes are rejected outright, which is failure-mode information an agent needs before calling. It stops short of saying what happens on a past timestamp or which permissions are required.

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, zero filler, and the core action-plus-condition is front-loaded before the timezone detail. Each sentence carries a distinct piece of information (what it does, the null/removal branch, the datetime format rule).

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, return values need no explanation, and all four required parameters are covered in the schema. The description supplies the timezone/format contract and the removal semantics, which is most of what an agent needs; only edge behavior (past timestamps, permission requirements, effect on an already-published poll) is unaddressed.

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 baseline is 3. The description goes beyond the schema by restating the critical constraint in prose — naked local datetime, timezone designators rejected, future-only — which is the exact thing an agent is likely to get wrong when filling scheduled_at.

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 specific verbs (schedule, reschedule, unschedule) against a specific resource (future publish or close action on a poll), which an agent can distinguish from immediate-action siblings like publish_poll or close_poll by the word 'future'. It never names a sibling explicitly, so differentiation is inferable rather than stated.

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 clearly explains the two modes of use within the tool (future datetime to schedule, null to remove), which is genuine usage guidance. However, it gives no guidance on when to choose this over publish_poll/close_poll (act now) or why a schedule might be preferred, so the alternative-selection question is left implicit.

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