create_event

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

With no annotations, the description carries the full behavioral burden and does surprisingly well: it discloses the end-time default (+1 hour), that repeats run forever unless repeat_count/repeat_until bounds them, that the two bounds are mutually exclusive, and exactly what warn_conflicts does ('a timed event is still created, but the result lists any events it overlaps under conflicts'). It omits permissions/auth requirements and what the call returns on success (e.g. an event id).

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?

Dense but front-loaded: the core create + start/end semantics come first, then repeat, alerts, conflicts, and metadata. Each clause covers a distinct parameter family with no filler, though the single unbroken paragraph makes lookup harder than a short structured list would.

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 tool with no annotations and no output schema, this covers parameter formats, defaults, and side-effects (conflict listing, unbounded recurrence) thoroughly. The remaining gaps — the required calendar identifier, permission requirements, and the success return value — are meaningful but narrow.

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 documents the non-obvious parameters in real depth: start/end ISO format, the all-day 'YYYY-MM-DD' convention and its midnight-based alerts rule, repeat/repeat_interval/repeat_days/repeat_count/repeat_until, alerts, status values, priority range, categories, url, and warn_conflicts. The required 'calendar' parameter is never explained (name or id?), and summary/location/description are left to their self-evident names.

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 opening sentence 'Create an event' states a specific verb and resource, which cleanly separates it from update_event, delete_event, and duplicate_event in the sibling list. An agent can identify the operation 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?

Usage is only implied – the description explains warn_conflicts behavior but never says when to prefer this tool over alternatives like propose_event, check_conflicts, or find_free_time, nor does it state prerequisites. For a straightforward create tool this is defensible, but there is no explicit when-to-use guidance.

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