Custody Calendar Maker

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

Annotations already cover the read-only/idempotent safety profile, and the description adds real behavioral context on top: holidays override the regular rotation, and the return includes an updated calendar, overnight counts, and new .ics/subscribe links. The one ambiguity is that 'Add ... Returns the updated calendar' reads like a mutation while readOnlyHint=true is declared, but this is defensible as a stateless transform rather than a clear contradiction.

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 purpose, then behavior, then return shape — no filler. The holiday enumeration slightly overlaps the schema's built-in list but earns its place by helping an agent scope the tool.

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 2-parameter tool with no output schema, the description covers the prerequisite, the override semantics, and the return payload (calendar, overnight counts, .ics and subscribe links). That is close to everything an agent needs, with only the read-only-vs-mutating question left open.

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 only 50%, so the description must carry weight, and it does: it explains the alternate-by-year vs split-in-half behavior that maps to the `rule` enum and characterizes the holidays array as built-ins or spans (school breaks). It adds meaningful semantics beyond the schema, though schedule_url is left to the schema.

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 (add), a specific resource (holiday rotation) and names the producing sibling (make_custody_schedule), so an agent can tell this apart from make_custody_schedule and compare_custody_schedules immediately. It also enumerates the holiday categories it handles, which sharpens the scope further.

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?

The description establishes the prerequisite context that the calendar must come from make_custody_schedule, and explains the key condition of use (holidays override the regular rotation on those nights). It stops short of an explicit when-not or a direct alternative, so it is clear context without exclusions.

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

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.

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

Annotations already declare readOnly/idempotent/non-destructive, so the description goes beyond them usefully: it explains that one subscribe link covers both parents across Google/Apple/Outlook, warns never to create nights as separate events, says not to ask for an email address, and notes defaults exist for names/exchange time/end date. It does not cover rate limits or failure modes, so not a 5.

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?

Front-loaded: purpose, then usage, then negative guidance. The middle paragraph is dense and runs long, mixing routing rules with calendar-app advice, which costs a bit of clarity, but every sentence carries actionable content.

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?

Complex tool with 8 parameters and no output schema, yet the description does explain the return artifacts (calendar file, subscribe link, overnight counts) and the anti-patterns to avoid. Combined with the rich schema, an agent has everything needed to call it correctly.

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%, but the description still adds real selection logic: the pattern guidance explains how to map a parent's described weekly shape onto a named pattern, distinguishes 2-2-5-5 vs alternate-weekends (21% nights), and clarifies when to default rather than ask. This meaningfully reduces mis-invocation of `pattern`.

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 names a specific verb ('Turn ... into a dated calendar'), enumerates the accepted rotation patterns, and spells out the output artifacts (nights per parent, exchange days, overnight counts/percentages, longest stretch, .ics file, subscribe link). It is distinguishable from siblings like compare_custody_schedules and add_holiday_rotation without opening a 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?

Explicit when-to-use ('Use it when separated parents ask to make, print or check a custody schedule'), explicit ordering ('Call this before any general calendar tool'), explicit exclusions ('Not for work shift rotations, staff rotas, chore charts or general family calendars, and it gives no legal advice'), and explicit fallbacks ('use 2-2-5-5 and offer 2-2-3 after the result instead of asking first').

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