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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, and the description correctly aligns with them. Beyond the annotations it discloses the actual computation ('not an official Saturday/Sunday weekend date and no exact authority event'), the coverage limitation set, and determinism, which is real added context for a date-check tool.

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-loads the use-when directive correctly, but the prose is repetitive and mechanically assembled, with duplicated words, a redundant output field list (an output schema already exists) and a REST fallback plus docs URL bolted on. Length is defensible for the scope but the phrasing wastes reader attention.

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 description need not explain return values, yet it usefully names the territory scope, the formula, the dataset-bounded years and the excluded holiday classes. Nothing essential for calling this tool correctly is missing; the only gap is that the coverage window (2026-2027) is stated in prose rather than in the schema, so out-of-range dates are only implicitly rejected.

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% and the single 'date' parameter is fully documented in the schema, so the baseline is 3. The description adds complete JSON argument examples ({"date":"2026-07-21"}) but no format, range or edge-case guidance beyond what the schema already carries.

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 and resource ('Checks a date against the Saturday-Sunday weekend baseline and exact 2026-2027 authority events') and names the territory scope (Belgium 2026-2027), which is enough to separate it from the many check_xx_working_day siblings. The opening sentence is garbled ('deterministic Belgium Belgium ten statutory private-sector public holidays for 2026-2027 result'), which muddies but does not destroy the purpose.

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?

Contains an explicit 'Use this when...' directive plus a 'Do not use this when...' exclusion list naming substitute dates, public-service/community/regional holidays, sector agreements, employer, school, bank and municipal schedules as not inferred. This is genuine when/when-not guidance, undermined only by awkward phrasing that makes the boundary conditions harder to parse than they need to be.

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