calendar.events.delete

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

With no annotations, the description carries the full burden and does well: it states irreversibility, the --readonly refusal condition, and the shape of the response (post-delete resource state or empty). It stops short of warning that deletion triggers guest cancellation emails by default (sendUpdates) and says nothing about recurring-event/instance deletion scope, which are the highest-risk side effects of this call.

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?

The most consequential facts — deletion, irreversibility, readonly refusal — are front-loaded before the generic mechanics. Some tokens are spent on boilerplate shared by every tool in this family ("[HTTP DELETE]", request-body construction), which dilutes rather than informs.

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 an 8-parameter destructive tool with no annotations and no output schema, the description covers the two things an agent most needs: what gets destroyed and what comes back. The gap is guest-notification side effects and recurring-event scope, though both are partly recoverable from the rich schema descriptions.

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 already documents eventId, calendarId, sendUpdates, sendNotifications, dry_run, query, params and body_file. The description restates the typed-flags-win-over-params precedence and body_file behavior, but that precedence is already stated verbatim in the schema — it adds no new semantics, so baseline 3 applies.

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 and resource ("Deletes an event") and explicitly enumerates the sibling operations on the same resource (get, import, insert, instances, list, move, patch, quickAdd, update, watch), so an agent can locate it within the calendar.events family without opening any schema.

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?

It implies usage (removing a resource) and notes it is refused under --readonly profiles, which is a real usage constraint. But the sibling list is presented as an unordered inventory rather than routing guidance — nothing says "use events.update to modify instead" or when deletion is the wrong choice over, say, moving an event to another calendar.

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