delete_event

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

No annotations were supplied, so the description carries the full burden and does so well: it states the original file is never modified unless in_place=true, the default output is '<file>.new', output_file must not already exist, dry_run writes nothing and only shows the patch, and all unrelated content (other events, VTIMEZONE, unknown properties) is preserved byte for byte. That is precisely the mutation-safety and side-effect profile an agent cannot infer from the schema.

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 primary action, then a clearly labeled SAFETY block, which is good structure for a destructive tool. A few clauses run long, notably the parenthetical about modified instances and the EXDATE sentence, but no sentence is 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?

For a destructive mutation with no annotations and seven parameters, the description supplies the safety model, default output path, overwrite constraint and preservation guarantee; with an output schema present it need not describe the return value. Only the undocumented 'calendar' parameter keeps it from being flawless.

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%, so the description must compensate, and it does for six of the seven parameters: event_uid, occurrence (with format and all-day variant), tz as the zone used to read the occurrence, dry_run, in_place and output_file. The 'calendar' parameter is never mentioned at all, and tz's role beyond occurrence parsing is not spelled out, leaving a real 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?

States a specific verb and resource (delete an event, addressed by UID) and immediately disambiguates the two deletion modes: whole recurring series with its modified instances vs. a single occurrence converted to an EXDATE. That distinction is exactly what an agent needs to pick the right behavior, and it separates the tool cleanly from update_event/create_event in the sibling 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?

Gives concrete when-to guidance for the ambiguous case: pass occurrence='2026-03-09T09:00' with a start value read in tz, or a bare date for an all-day event, and an EXDATE is added instead of removing the series. It also explains when to set in_place, output_file and dry_run. It stops short of naming a sibling alternative (e.g. update_event for property edits), so routing guidance is implied rather than explicit.

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