update_event

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

With no annotations, the description carries the full burden and does so: it states the original file is never modified unless in_place=true, that output_file must not exist yet, that dry_run writes nothing, and that unrelated content is preserved byte for byte. It also discloses side effects beyond the requested change (DTSTAMP refresh, SEQUENCE increment) — exactly the kind of hidden mutation an agent needs to know before calling.

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 paragraphs split cleanly between semantics and safety, with the mutation-scope rule front-loaded. Every sentence carries distinct information — field update rules, side effects, file-write guarantees — and there is no restatement of the tool name or filler.

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 exists, so return-value explanation is not required, and the description covers the risky parts (file writes, dry run, series scope) thoroughly. The remaining gaps are the undocumented duration_minutes parameter and the accepted values for status/transp/rrule, which an agent must guess.

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 0%, so the description must compensate and largely does: it defines the empty-string removal convention, the replace-not-merge semantics of attendees, the start-without-end behavior, the tz default, and the roles of in_place, output_file, dry_run, and calendar. It leaves duration_minutes entirely unmentioned and gives no value hints for status, transp, or rrule format, so some of the 16 parameters remain opaque.

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 and resource ('Change fields of one event') and immediately scopes it ('the whole series if it recurs'), which distinguishes it from create_event and delete_event. The sibling set contains no other mutator of an existing event, so no further differentiation is needed.

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?

Gives explicit usage rules: only passed fields change, empty strings remove fields, attendees replaces the list, and single-instance modification 'is not supported', which routes the agent away from an unsupported case. It also defers to create_event for all-day conventions. It stops short of naming alternatives for the unsupported case or stating prerequisites such as needing the file to be writable.

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