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

Annotations cover safety (readOnly, idempotent, non-destructive, openWorld=false), and the description goes well beyond that: it states the counting formula, that shortened days still count as one planning date, that no substitute/bridge day is invented, and that no full-day rest is added by national-importance dates. It also discloses the REST fallback endpoint and docs URL, which an agent needs for reliability.

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-to-use guidance is front-loaded, but the body repeats the national-importance/shortening rule several times and enumerates a long Outputs list that duplicates the existing output schema. The unparseable 'Do not use this when...' sentence is dead weight that costs clarity.

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, a full output schema, and 100% schema coverage, the description supplies the remaining context an agent needs: eligibility, counting formula, scope boundaries, and a direct API fallback. The only gap is the mangled exclusion clause, which leaves the when-not condition partly ambiguous.

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 schema already documents all five parameters including the required enum and the date formats. The description only re-lists the input names without adding syntax, constraints, or defaults beyond the schema, so the baseline 3 applies.

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 names a specific verb (counts) and resource (Estonia working/non-working dates) and has a dedicated 'What it computes' clause that defines the counting rule. It is distinguishable from the many count_*_working_days siblings by the explicit Estonia scope, though it never names an alternative sibling to route against.

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?

It gives a positive trigger ('auditable Estonia working-day count... call directly instead of answering from memory') and enumerates clear exclusions (individual shifts, actual hours, opening hours, payroll, legal deadlines, future years). The 'Do not use this when...' sentence itself is garbled and unparseable, so the exclusion condition is muddier than it should be.

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