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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds behavior beyond that: it is a facts-only comparison, explicitly not legal advice, and it discloses what is actually computed (overnights, percentages, exchanges/month, longest absence). It does not discuss the time horizon or pagination, but for a read-only comparison tool this is solid added context.

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?

Three sentences, front-loaded with the verb, the range, and the computed outputs, followed by when-to-use and the exclusion. No filler; the heavy pattern taxonomy lives in the schema rather than bloating the description.

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?

There is no output schema, but the description compensates by naming the returned metrics, and annotations carry the read-only safety profile. The remaining gaps are the default/behavior of 'months' and the role of parent_a/parent_b, which an agent would have to guess.

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 40%: 'patterns' is richly documented in the schema itself and 'start_date' has its format, while 'months', 'parent_a' and 'parent_b' are undocumented in both places. The description does add meaning the schema lacks by clarifying the 2-to-6 rotation cap and the shared start date, but it never explains the months window or what parent_a/parent_b labels do.

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 (compare) and resource (custody rotations), plus the scope (2 to 6, same start date) and enumerates the exact metrics returned: overnights and percentage per parent, exchanges per month, longest time away from each parent. An agent can distinguish it from make_custody_schedule and add_holiday_rotation without opening any 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?

Gives an explicit trigger ('Use it when parents ask which custody schedule to choose, or how week on/week off differs from 2-2-5-5 or 2-2-3') and an explicit exclusion ('Not for work shift patterns'). However it never names the sibling tools it should route to when the user actually wants a schedule created or a holiday rotation added, so sibling disambiguation is left implicit.

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