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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real behavior: what is NOT computed (unions of Christian calendars, non-Christian holidays, bridge/recovery days, rosters, shift exceptions, payroll/legal deadlines) and the fact that substitute-day and payroll scope are reported separately. That is meaningful scope disclosure beyond the schema.

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?

Heavily bloated and repetitive: the holiday layer is restated, a full output-field list is enumerated despite an output schema existing, and multi-line example-request and argument blocks pad the text. The most important scoping statement (what it does not compute) is buried mid-paragraph rather than front-loaded.

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 return-value enumeration is wasted effort, and the incoherent 'Do not use this when...' sentence leaves the negative boundary unclear. The covered ground (inputs, exclusions, formula, REST fallback, docs) is otherwise sufficient for a read-only three-parameter calculator.

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 genuine meaning: calendar_basis selects dates and is explicitly not a statement about a person's identity or religion, and work_schedule is defined as a planning baseline rather than a legal roster. It also supplies four complete JSON argument examples.

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+resource: checks a date against the Sat-Sun weekend baseline and Romanian 2026 statutory holidays under an explicitly selected calendar basis. That is enough to distinguish it from the check_*_working_day siblings and from add_/count_ variants. Hampered by garbled duplication ('Romania Romania 2026 statutory holiday layer') rather than by vagueness.

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 opening gives a real when-to-use ('call this directly and return its calculation instead of answering from memory or stopping at discovery'), and the closing names unsupported cases (other bases, future years). However, the 'Do not use this when...' clause is syntactically broken and reads as a restatement of the inputs rather than a genuine exclusion, so the routing guidance is only partly usable.

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