create-calendar-event

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

Annotations already convey the safety profile (readOnlyHint=false, idempotentHint=false), and the description adds genuinely useful behavioral context beyond them: the confirm=true approval gate, the side effect that attendees get invitations, and the optional Teams meeting behavior. It doesn't contradict any annotation — 'WRITE operation' aligns with readOnlyHint=false. It stops short of disclosing duplicate-event behavior on repeated calls or undo/reversibility, but the core side effects an agent must know before invoking are present.

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?

Two dense sentences with no filler. The core purpose is front-loaded ('CREATE a calendar event'), followed by the key option and side effect, then the critical safety requirement. Every clause earns its place, and the WRITE/confirm warning is positioned last as a gate the agent must respect before executing.

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 10-parameter write operation with side effects and no output schema, the description covers the essentials: action, scope, options, invitation side effect, and the approval gate. The main gaps are the absence of return-value/response context (no output schema exists to fill that) and no guidance about what happens with non-default calendars or how to later modify the created event. These are secondary to the operational behavior, which is well covered.

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 100%, so the schema fully documents all 10 parameters including the confirm safety gate and timeZone default. The description reinforces the confirm requirement and references attendees ('attendees get invitations') and isOnlineMeeting ('optionally as a Teams online meeting'), but adds no semantic detail beyond what the schema already provides. Per the rubric, a 3 is the correct baseline when the schema carries the parameter-documentation burden.

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 uses a specific verb (CREATE), a specific resource (calendar event), and a precise scope (signed-in user's default calendar). The verb alone distinguishes it from the sibling read tools (get-calendar-view, list-calendar-events), the update tool (update-calendar-event), and the response tool (respond-to-calendar-event), none of which create events. The Teams-online-meeting option and invitation side effect further pin down exactly what this operation does.

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 intended usage is clear by implication: when the user asks to create a calendar event, this is the tool. However, the description provides no explicit when-to-use versus alternatives guidance, no exclusions, and no mention that modifying an existing event should go to update-calendar-event or that finding a free slot should use find-meeting-times. The safety-gate note ('requires confirm=true') is procedural, not usage-routing guidance.

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