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

Annotations only declare destructiveHint=true; the description adds the crucial behavioral detail that nothing happens until confirm: true and that the default is a preview. It also discloses the out-of-band limitation that connecting requires a browser. It does not say what is destroyed on disconnect (stored tokens, synced events, existing mappings), which is the main open risk for a destructive operation.

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?

One sentence plus two short parentheticals; the core action is front-loaded and both asides carry non-redundant information (out-of-scope connect path, confirm gate). Nothing to trim.

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 single-parameter, destructive, confirm-gated mutation with no output schema, the definition covers the action, the safety gate, and the out-of-scope sibling workflow. The remaining gap — what state is lost and whether the call is reversible — is meaningful but not fatal for a tool whose annotations already flag destructiveness.

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 coverage is 100% and the confirm parameter is fully documented in the schema, including its default and preview semantics. The description's parenthetical merely restates that gate, adding no syntax or consequence beyond it — baseline 3 is appropriate.

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 ('Disconnect the coach's Google Calendar'), which is unambiguous against the rest of the calendar-related surface. It does not name its closest sibling (start_google_calendar_connect / get_google_calendar_status) by name, instead alluding to 'connecting' generally, so differentiation is implicit rather than explicit.

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 tells the agent the connection path is out of scope ('Connecting needs a browser sign-in; do it in the web app'), steering it away from trying to connect via this tool, and it states the confirm-gated invocation pattern. What's missing is explicit routing for the reverse case — e.g. 'call get_google_calendar_status first to check if a calendar is connected'.

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