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

Annotations declare readOnlyHint=false, destructiveHint=true, and openWorldHint=false, and the description agrees with all three — no contradiction. Beyond the annotations, it discloses two non-obvious behaviors: title/start/end specify the complete new state (replacement, not a partial patch), and the all-day/timed conversion (an all-day event becomes timed if timestamps are passed, and vice versa). Neither is inferable from the schema or annotations alone.

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 dense sentences with the most critical constraint (own-created events only) front-loaded. The second sentence partially restates the first ('created itself' vs 'created by anyone else are not addressable'), a minor redundancy, but every other clause earns its place and nothing is padding.

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?

An output schema is present, so return-value documentation is unnecessary. The description covers the closed-world scope, replacement semantics, and all-day conversion, while the schema covers ISO formats, all_day forcing, and time_zone behavior. The one noticeable gap is the fate of omitted optional fields (location, description, calendar_id, time_zone) on update — unclear whether they are preserved or cleared — but annotations and the output schema carry much of the remaining burden.

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 56% — start, end, all_day, event_id, and time_zone are well documented, while title, location, calendar_id, and description have no text. The description adds a valuable cross-parameter insight (the required trio constitutes the complete new state, and the start/end format drives all-day vs timed), but it does not compensate for the undocumented optional parameters. This lands at baseline.

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?

The description uses a specific verb and resource ('Updates an event') and immediately narrows the scope: only events 'THIS access created itself (via event_id from create_event),' with events created by anyone else 'not addressable.' This clearly distinguishes it from siblings like search_events, get_availability, and create_event, so an agent can select it correctly 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?

The description states an explicit when-not: events created by anyone else are not addressable, preventing the agent from attempting updates on foreign events. It also ties event_id to create_event, which implies the creation prerequisite. However, it never names an alternative sibling for routing, so it stops just short of the full five.

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