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

Annotations already declare non-read-only, destructive, idempotent, and closed-world, so the safety profile is covered. The description adds genuinely useful context beyond that: the change must be against the current version (concurrency guard) and provider-owned events are off-limits. The phrase "cannot delete" is about the event resource itself and is not strictly contradicted by destructiveHint=true (which covers overwriting fields), but the interplay is left for the agent to infer.

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 dense sentences, front-loaded with the usage condition, then the time-handling caveat. No filler, though the second sentence packs two distinct ideas (timezone labeling and instant semantics) that an agent parsing quickly must disentangle.

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 a rich schema and an output schema present, the description need not restate fields or returns. It covers scope, concurrency, and time interpretation, which are the highest-risk gaps for a 6-parameter mutation with nested objects. Error handling for a version mismatch and the replace-vs-merge nature of the change sets are only in the schema, but the essentials for a correct call are present.

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; the description earns above that by clarifying expectedVersion semantics (must match the current version from a read) and the timed-event time semantics (startAt/endAt are instants with offset, not local clock values, and displayTime.label is the household-timezone representation). That last point references a read-side field not in this schema and would otherwise be easy to get wrong.

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 (change) and resource (ComingUp-owned event or occurrence) and immediately bounds scope: it cannot delete or write provider events. That distinguishes it cleanly from create_event, get_event, and the read-side siblings in a crowded tool list.

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 change ... with its current version" plus the explicit exclusion of provider events and deletion gives real when-to-use guidance. It stops short of naming the sibling to use instead (e.g. create_event for new events, get_event to fetch expectedVersion), so the routing is implied rather than complete.

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