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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the description is not carrying the full safety burden, but it adds genuinely new context: the required `integrations:write` scope and the fact that the first call is a validation-only dry run that returns a summary and confirm_token. It does not say what the destructive effect actually is (replacing an existing default calendar) or how failures on the second call surface.

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 short sentences, front-loaded with purpose, then the permission requirement, then the call sequence. Nothing is repeated and the confirm/approval instruction lands last where it is most actionable.

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 destructive, open-world mutation with no output schema, the description covers the call choreography and permission well, but leaves out what 'choosing' does to any previously configured calendar, where to source provider and calendar_id, and what the summary/confirm_token response looks like. Enough to avoid the worst mistake, not enough to call it confidently on the first try.

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 only 33%, and the two required parameters, provider and calendar_id, are bare untyped strings with no description in the schema. The description does not compensate: it never explains valid provider values, the calendar_id format, or that these come from list_integration_calendars. Only confirm_token is addressed, and that is already documented in the schema.

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 concrete verb and resource ('choose the calendar my bookings go to') that is clearly distinct from the read-only siblings list_integration_calendars and list_integrations, and from sync_integration. An agent can identify the tool's effect without opening the 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 spells out the exact two-call protocol and the gating condition: show the summary to the person, and only call again with confirm_token after they agree. It does not say when to prefer this over list_integration_calendars or how to obtain valid provider/calendar_id values, which is a real gap.

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