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

Adds substantial context beyond annotations: reminders can fire after the agent exits, delivery respects stop/mute and active membership, limits are given, and return values (scheduled time, state, delivery warning) are described. Minor gap: it does not clarify whether cancellation or scheduling carries side effects an agent should warn the user about, and the requestId retry semantics sit in mild tension with idempotentHint=false.

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?

Front-loaded with purpose and mode routing, then constraints, then return values, then exclusions, then a reference link. Dense but nearly every clause carries information; the single run-on paragraph is harder to scan than a short bulleted mode list.

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 multi-mode tool with no output schema, the description supplies return shape, limits, delivery caveats, idempotent retry guidance and a docs link. An agent can act correctly without opening anything else.

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?

With 55% schema coverage over 11 params, the description meaningfully compensates for the key fields: body+inMinutes/at requirement, explicit UTC offset, requestId retry semantics, reminderId outcome lookup, and cancelReminderId. It leaves env, title, agentName, machineId and sessionId unexplained, which are presumably housekeeping fields.

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?

Opens with specific verbs (schedule, list, retrieve, cancel) applied to a precisely scoped resource: a personal Pushary reminder for the authenticated user. The closing exclusion ('Does not schedule agent work or customer campaigns') plus sibling context makes the boundary unambiguous.

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?

Each invocation mode is routed explicitly: no arguments lists pending, reminderId retrieves outcome, cancelReminderId cancels, and scheduling requires body plus inMinutes or at. Constraints (one-time only, 30 days, 25 pending per user/site) tell the agent when an attempt will fail.

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