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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered; the description adds the genuinely useful semantics that 'holidays override the regular rotation on those nights' and that the call returns an updated calendar, overnight counts and new .ics and subscribe links. The write-sounding verb 'add' alongside readOnlyHint is a mild tension, but the return-value sentence makes clear this is a generator rather than a mutation of stored state, so it does not rise to a 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?

Front-loaded with purpose, then override rule, then return values in three tight sentences. The long list of US/UK/Canadian/Australian holidays and school breaks is somewhat redundant with the schema enum, which is the only slack in an otherwise efficient 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?

With no output schema, the description carries return-value disclosure itself and does so (updated calendar, overnight counts, .ics and subscribe links), plus the required input provenance. It lacks any note on error handling or what happens with conflicting/overlapping holiday entries, which keeps it short of complete for a tool with a nested item object.

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 50%, and the description's holiday enumeration largely duplicates the schema's `holiday` enum rather than adding format details. The one net-new nugget is the rotation semantic ('alternating by year or split in half'), which elsewhere is documented in the `rule` property itself, so the value added over the schema is marginal.

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 plus resource ('add a holiday rotation to a custody calendar') and immediately names the sibling that produces the input ('made by make_custody_schedule'), so an agent can distinguish it without opening a schema. It also enumerates the holiday categories covered and the override behavior, which disambiguates it from compare_custody_schedules.

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 precondition is clear: the calendar must come from make_custody_schedule, and schedule_url is described in-schema as 'any link returned by make_custody_schedule (view, download or subscribe)'. However, it never states when not to use it or how it relates to compare_custody_schedules, so the routing guidance is context-rich but not exhaustive.

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