outlook_create_event

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

Goes well beyond the annotations: it warns that `is_online` is silently ignored on consumer mailboxes (with the exact failure shape Graph returns), that Teams meetings need a work/school account, that `recurrence` produces a series rather than a single event, and that omitting `show_as` defaults to busy. These are non-obvious backend behaviors an agent could not get from `destructiveHint: true` alone.

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 a one-line summary plus a concrete call example, then ordered by parameter importance. It is long, but the length is earned by 13 undocumented parameters and several genuinely surprising behaviors; a few sentences (the full Graph JSON example, the repeated noEnd warning) could be tightened without losing information.

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?

No output schema exists, so the description would ideally say what comes back (an event ID? retrievable via outlook_find_event_by_key using `key`?) — that link is left implicit. Otherwise it covers the mutation semantics, account-type constraints, and defaulting behavior needed to call this correctly.

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 0% schema coverage across 13 parameters, the description does the heavy lifting: it defines the accepted values of `show_as` (a de-facto enum), the IANA format for `timezone` with an explicit anti-pattern (never "PDT"), the ISO 8601 format for start/end, the dual string-or-object shape of `recurrence`, and the meaning of `key`. `body`, `location`, and `is_all_day` are left undefined, which is why it falls short of a 5.

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 a specific verb+resource ("Create a calendar event") and enumerates the salient optional dimensions (attendees, recurrence, busy status, online meeting). An agent can distinguish it from outlook_update_event/outlook_delete_event by verb alone, but the description never names those siblings or states the boundary explicitly.

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?

Rich conditional guidance: use the shorthand recurrence strings for the common cases and the full Graph object "for anything else," prefer a bounded range when attendees exist, omit `calendar` for the default. What's missing is routing against siblings (e.g. use outlook_update_event to modify an existing event) — the agent must infer the create-vs-update boundary.

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