update_event

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

No annotations are present, so the description carries the full burden and does so well: it discloses merge semantics, the exact clearing conventions ('' / [] / 0 clears; [] removes all alerts), the series-wide blast radius on repeating events, and the all-day date convention. It stops short of permissions/error behavior and there is no output schema to cover returns.

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?

Six dense lines, purpose first, then one clause per parameter group. Nothing is padded and the unusual semantics are front-loaded ahead of the routine clearing rules.

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 17-parameter mutation with no annotations, no output schema and no per-parameter schema docs, the description covers the behavioral essentials an agent needs to avoid destructive mistakes on merges and series. The missing pieces — return value, permissions, error cases — are secondary but real.

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 0% across 17 parameters, so the description must compensate — and it does for the parameters whose semantics are genuinely non-obvious: start/end date format and all-day meaning, repeat values plus 'none'/omit, alerts units and replace behavior, and clear-vs-omit for url/categories/status/priority. The remaining fields (summary, location, description, uid, calendar, repeat_*) are either self-evident by name or deferred to create_event, leaving a residual gap.

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?

Opens with a specific verb+resource+identifier: 'Update fields of an existing event by uid.' An agent can immediately separate this from create_event, delete_event, move_event and duplicate_event. The partial-update scope ('Only provided fields change') further pins down what kind of update this is.

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?

Strong context for how to call it (partial update, omit-to-leave-alone, series-wide effect) and it routes the agent elsewhere for the repeat_* options ('see create_event'). It does not, however, address when to prefer this over move_event or duplicate_event, so the sibling boundaries are only partially drawn.

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