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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds real context beyond them: privacy of the created event, the guarantee the due date is not modified, and the missing[] failure mode. It also discloses a cost ($0.05) and an API-key requirement, which annotations cannot express. However, return shape and retry semantics are left to the schema and output schema rather than described, so this is solid additive context rather than a full behavioral picture.

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?

Purpose is front-loaded, followed by the when-to-call rule, then the parameter recipes and the failure mode. The telegraphic style ("Timed: date, start_time, timezone, and end_time or duration_minutes") is dense but each clause carries information. A slightly less compressed phrasing of the mode recipes would read more cleanly, but nothing is wasted.

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 13-parameter write tool with a rich output schema, the description covers the decision-relevant parts: authorization by the user, required timing combinations, failure behavior, cost, and the repeat-session flag. Small gaps remain, such as how end_date interacts with all_day for multi-day reservations, but the schema and output schema absorb parameter-level and return-value detail.

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 100%, so the schema already documents every parameter, which sets the baseline at 3. The description does add genuinely useful conditional semantics the schema cannot: the valid timed combination (date, start_time, timezone, and end_time or duration_minutes) versus the all-day combination (date plus all_day true). That pushes it slightly above baseline, but it does not explain end_date or the request_id/idempotency_key alias interplay, so it stays near the baseline band.

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 opens with a specific verb and resource ("Reserve calendar time for a to-do") plus the exact key it operates on (todo_id), and immediately states the effect: creates one private linked event while leaving the to-do and its due date untouched. That distinguishes it clearly from mutation siblings such as reschedule_todo_session, unschedule_todo_session, and complete_todo.

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 gives explicit preconditions ("Call only when the user told you to schedule it and gave the timing"), an explicit exclusion ("If you are only suggesting slots, say them and do not call this"), and a routing rule for the repeat case ("add_session true is required for a second session"). It also tells the agent what to do on incomplete input: ask rather than guess.

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