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

Annotations cover the read-only/idempotent safety profile, and the description adds substantial context beyond them: 422 outcomes for no_next_run and for invalid expression/start/zone, that these are not charged, the `exhausted: true` flag for rare schedules, expected latency (~0.1 s), price (USD 0.001) and the free 10/day quota. This is exactly the extra behavioral detail annotations cannot carry.

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: purpose and alternative first, then grammar, then edge-case behavior, then cost. The pricing/quota/docs tail is useful but slightly heavy relative to the core call semantics, keeping it short of a 5.

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 structure needn't be restated, and the description still flags the notable `exhausted: true` case. Between annotations, full schema coverage, the output schema, and the description's error/pricing/grammar coverage, nothing needed to invoke this correctly is missing.

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 100%, so count/start/timezone are fully documented in structured data (baseline 3). The description goes further on the required `expression` parameter by explaining Vixie OR semantics between day-of-month and day-of-week and the accepted grammar, which is meaning the schema does not convey.

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+resource ('the next run times of a cron expression') and immediately names the sibling it is not ('For iCalendar RRULEs use expand_rrule'). An agent can distinguish it from expand_rrule without opening either 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?

Explicitly routes to expand_rrule for RRULEs, and enumerates when the tool applies (5-field cron or macro) plus what it rejects (no seconds/year fields, no R/H/W). The never-fires and invalid-input cases are called out, so the agent knows the boundary conditions.

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