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

Annotations only declare the safety profile (non-read-only, non-destructive, non-idempotent, closed-world). The description adds genuinely useful behavior: friends added are notified, email addresses without an LFG account receive an invitation, and the call returns the alarm, its next ring time, its link and a share picture. The 'date or repeat days, never both' constraint is also disclosed, which is exactly the kind of cross-field behavior the schema does not state.

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 front-loaded sentences: purpose first, then boundary conditions, then side effects and return value. Dense with clauses but every sentence carries distinct information; 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?

Despite 23 parameters, nested objects and no output schema, the description covers the required inputs, the one-off vs repeating split, side effects on added people, and the return payload. The many optional styling fields (vibe, theme, snooze, wallpaper) are left to the 96%-covered schema, which is a reasonable division of labor.

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 96%, so the per-field semantics are already handled; the baseline would be 3. The description rises above it by stating the mutually exclusive pairing of date vs repeat_days and the required time + IANA time zone, a schema-level relationship no individual property description captures.

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 a specific verb and resource with scope: an alarm that rings at a clock time, either once on a date or on repeating weekdays. It also explicitly carves itself out from the sibling family, noting it 'does not watch anything online' and that an event with a Luma/Partiful link is a different alarm, so an agent can separate it from set_event_alarm, set_webhook_alarm, set_post_alarm and the price/trader alarms.

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?

Gives clear usage context ('a wake-up, a meeting, a reminder') and an explicit exclusion for link-watching / event-link alarms. It stops short of naming the sibling tool to use instead (e.g. set_event_alarm), so routing is implied rather than fully specified.

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