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

Annotations already declare readOnly/idempotent/non-destructive, yet the description goes well beyond them: it discloses the exact formula, that seven named state holidays are non-rest, that no bridge/substitute day is invented, and enumerates out-of-scope domains (payroll, legal deadlines, individual rosters, future years). This is unusually rich policy context for a read-only calculator.

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 when/when-not framing is front-loaded, but the block is long and includes malformed sentences and a 'Counts Slovenia working days around X is ...' example pattern that reads as broken. It also re-lists the full output field set even though an output schema exists, adding length without new information.

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?

For a read-only calculator with full schema coverage, an output schema, and rich annotations, the description covers scope, formula, exclusions, an input example, and a documented REST fallback plus docs link — nothing an agent needs is missing. The only shortfall is the muddled exclusion clause, which slightly undermines an otherwise complete definition.

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 the schema already documents all five parameters, and a complete JSON argument example reinforces the required set. The description adds only a restatement of the work_schedule enum meaning ('explicit Monday-Friday planning baseline; not an individual legal roster'), which the schema also states, so a baseline 3 is warranted.

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 ('Counts authority-scope working and non-working dates in a range') scoped to Slovenia, clearly distinguishing it from the many sibling count_*_working_days tools. An agent can identify the tool as the Slovenia planning-baseline counter without opening the schema.

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?

Opens with an explicit 'Use this when' trigger and adds 'Call this tool directly... instead of answering the formula from memory,' which is genuine routing guidance. The 'Do not use this when' clause is present but garbled ('when slovenia 2026 statutory work-free dates over an explicitly selected Monday-Friday planning baseline'), so the exclusion criteria are harder to act on than they should be.

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