calendar_feed_enable

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

Goes well beyond the annotations: it discloses the exact event model (all-day events, 09:00 alarms, remindDaysBefore and fiscal 3-day/1-day thresholds), that filed declarations and renewed items drop out at refresh, and that regenerate invalidates older links. It also flags the critical security trait — the link is a bearer credential that must only be shown to the user — which no annotation conveys.

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?

Front-loaded with the action and idempotency note, then behavior, then return contract, then the safety warning — a sensible ordering. The long inline enumeration of return fields is justified because there is no output schema, though it is denser than ideal.

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?

With no output schema, the description fully carries the return contract (both enabled and disabled shapes, all field names) and covers event behavior, invalidation, and credential handling. An agent has everything needed to call it and relay results safely.

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% so the baseline is 3, but the description adds real meaning about consequences: regenerate kills every older link, and the include flags determine the event populations plus the drop-out behavior at refresh. It stops short of stating defaults explicitly (those live only 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 specific verb and resource ('Turn on the calendar subscription') and immediately scopes it with the idempotency behavior. The enable-vs-regenerate distinction makes it clearly separable from the get/update/disable siblings.

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?

Explains when the default path applies (existing subscription keeps its link) and gives an explicit condition for the alternative (regenerate=true when a new link is wanted, invalidating old ones). It never names the sibling tools (calendar_feed_update, calendar_feed_get), so routing between tools is implied rather than stated.

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