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

Annotations already declare readOnlyHint=true, and the description confirms it with 'Changes nothing.' More valuably, it discloses the computation basis (schedule vs contract, per the absence policy) and a hard 366-day limit that the agent could not otherwise know. It stops short of describing error behavior when the period is exceeded.

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?

Two tight sentences plus the endpoint: the computed quantity, its basis, its limit and its safety profile are all front-loaded with no filler.

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 usefully specifies the return shape ('per day and in total'), the source of the computation and the period cap, which is enough for correct invocation. It omits what happens at the 366-day boundary and whether the day-by-day output can be empty for non-working days.

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 the baseline is 3, but the description adds meaning beyond the schema: the 366-day cap constrains how start_date/end_date may be paired, and 'from the schedule or the contract' explains why absence_type_id matters. It still does not map individual parameters to semantics.

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 computed resource: the expected hours an absence would cost, per day and in total. It is clearly distinguishable in kind from sibling readers like shiftbase_get_absence (recorded absence) and shiftbase_list_absences, though it never names a sibling or says which to prefer.

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 implies the use case (previewing the hour cost of an absence before requesting one) and discloses the 366-day period constraint, but gives no explicit when-to-use or when-not-to-use guidance relative to get_absence, list_absences or request_absence.

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