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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true. The description adds that unknown or other-user event_id returns an error and does not create a row (consistent with idempotency), that it rebuilds life_state, and the cost/authentication constraints. It doesn't contradict annotations and provides useful extra behavior details, but doesn't go into return format or detailed side effects.

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?

The description is information-dense but well-structured: it leads with the mutation verb, required parameter, then optional patch duplicates, followed by error behavior, alternative tool, side effect, auth, and cost. Every sentence adds necessary context without redundancy. Slightly long but justified given the tool's complexity.

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 tool with 17 parameters and existing annotations and output schema, the description covers the essential operational aspects: required event_id, optional fields, error semantics, alternative tool, lifecycle side effect, authentication, and cost. It doesn't explain the return value, but output schema exists. It's complete enough for an agent to call correctly without further research.

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 82% (high), so baseline is 3. The description adds value by consolidating the patchable fields, pointing to log_event for the full field list, and clarifying aliases (date/event_date, time/event_time, people/with/person_ids). It also notes that location, description, event_time are cleared on empty/null. This goes beyond the schema's individual field descriptions.

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 starts with 'MUTATES one existing calendar event the authenticated user owns', clearly stating the verb, resource, and ownership requirement. It lists the required event_id and the optional patchable fields, and explicitly distinguishes from log_event (creating new) and update_food (for meals). This is precise and differentiates well from siblings.

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?

It provides an explicit exclusion: 'For food-diary meals, prefer update_food (it syncs the mirrored event).' It also states prerequisites (API key or OAuth, share tokens cannot write) and the error behavior for unknown/other-user event_id. However, it doesn't explicitly contrast with log_event beyond implying update-vs-create, so a small gap remains.

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