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

Annotations already declare readOnly=false, destructive=false, idempotent=true and openWorld=false, so the safety profile is covered. The description usefully adds the write-scope boundary (ComingUp-owned only, no provider calendar writes), but says nothing about permissions, what happens on replay with a duplicate idempotencyKey beyond the schema's one-liner, or notification side effects.

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 sentences, no filler, with the usage condition and its exclusion front-loaded before the time-interpretation caveat. Every clause carries information the schema and annotations do not.

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 nested, oneOf-heavy create tool with 8 parameters, an output schema, and rich annotations, the description covers the two things structured data cannot: the ownership boundary and the instant-vs-local time trap. It could go further on permissions or recurrence expectations, but nothing essential for a correct call is missing.

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?

At 75% schema coverage the schema does most of the work, but the description contributes a genuinely non-obvious semantic point: startAt/endAt are instants rather than local clock values, which changes how an agent constructs them. The advice to prefer displayTime.label in the household timezone is helpful but references a field absent from this input schema, which risks confusion about where that value comes from.

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 ("create a ComingUp-owned event") and immediately bounds it with a negative scope ("cannot create or write provider calendar events"), which cleanly separates it from write paths that touch external calendars. It stops short of naming the sibling it hands off to, or of distinguishing itself explicitly from update_event/get_event, so it is clear but not fully sibling-differentiated.

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?

"Use this when you need to create a ComingUp-owned event" gives an unambiguous trigger, and the provider-calendar exclusion states when not to use it. It does not point at an alternative tool for the excluded case, leaving the agent to find that path itself.

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