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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description goes further with genuine behavioral context: the exact formula, the exclusion of union calendars/rosters/payroll/legal deadlines, the required explicit calendar_basis, and a direct REST fallback with a warning not to guess other /api/* paths. It does not discuss error behavior or dataset staleness beyond naming dataset_version.

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?

The block is long and partly incoherent: the 'Do not use this when...' sentence is ungrammatical, and the 'Example user requests' lines are broken fragments ('Count Romania working days around January 24 remains a statutory holiday even on Saturday'). It also enumerates the entire output field list even though an output schema exists, and repeats the formula and examples already in the schema. Useful information exists but is poorly organized and padded.

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 the exhaustive returns list is unnecessary, and the schema covers all six parameters. What the description does uniquely contribute is scope denial (no personal roster, no payroll/legal deadlines, no calendar unions) and the REST fallback URL, which is real added value. The garbled usage fragments leave the completeness slightly short of the richness this tool could support.

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 100%, so parameter meaning is already fully carried by the schema (including the religion-inference warning for calendar_basis and the Monday-Friday planning caveat for work_schedule). The description restates the input list and repeats the calendar_basis advice, adding little beyond the schema; the JSON examples duplicate the schema examples. Baseline 3 is appropriate.

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 states a specific verb and resource ('Counts authority-scope working and non-working dates in a range') scoped to Romania, which lets an agent place it against the many count_*_working_days siblings. It does not explicitly name its nearest siblings (add_ro_working_days, check_ro_working_day), so the differentiation is by country scope rather than by operation, but the purpose itself is unambiguous.

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?

There is a clear trigger ('Use this when you need an auditable Romania working-day count') and a strong directive to call the tool rather than answer from memory. The 'Do not use this when...' clause is a garbled fragment that never names a coherent alternative tool or condition, so when-not guidance is effectively missing. Scope exclusions (no rosters, payroll, bridge days) are useful but describe coverage limits, not sibling selection.

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