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

Annotations already establish read-only/idempotent/non-destructive, and the description adds real behavioral scope: the exact computation formula, that it distinguishes statutory rest days from named non-rest holidays, that it is snapshot-bound ('later legal changes require a new snapshot'), and explicit out-of-scope items (payroll premiums, leave rights, retail closures, shift/bank/school schedules). The malformed exclusion sentence slightly muddies this.

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 middle section is a run-on with a broken sentence, duplicated holiday facts, and a full output-field enumeration that duplicates the output schema. The genuinely valuable pieces (formula, REST fallback, docs link) are buried 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?

With annotations and an output schema present, the description only needs to cover scope and behavior, which it largely does: computation definition, exclusions, snapshot limitation, and a direct REST fallback. The garbled when-not clause is the one substantive gap.

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% and both parameters are documented there (including the signed-offset and excluded-start-date semantics), so the schema does the heavy lifting. The description only restates 'start_date (date); working_days (integer)' plus an example, adding no semantics beyond the schema.

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: 'Adds or subtracts Slovakia authority-scope working days in exact coverage,' which is clearer than the bare name. However, it never explicitly contrasts itself with the adjacent siblings add_* / count_sk_working_days / check_sk_working_day, leaving the country-prefix convention to carry differentiation.

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 usable positive trigger ('when you need a deterministic Slovakia working-day offset') and tells the agent to return the tool's result rather than derive it from memory. The 'Do not use this when...' clause is malformed — it never states an actual condition, instead dumping holiday facts — so the when-not guidance is effectively unusable.

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