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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety bar is met. The description adds meaningful behavioral context beyond that: deterministic output, no inference of Order 330 adoption, conditional (not full-day) shortening, and separate treatment of statutory rest vs non-rest observances. The no-inference rule and shortening caveat are genuinely useful, though the value is diluted by repetition.

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 description is heavily bloated: a redundant 'Latvia Latvia' opening, near-duplicate requirement statements ('Explicit ... required' repeated thrice), six inline JSON examples duplicating the schema's own examples, and a full re-listing of output fields despite an existing output schema. Sentence fragments ('What it computes:', 'Formula:') pad length without adding selection value.

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 three-param, fully-enumerated tool with an output schema, the description covers the essentials: scope, exclusions, formula, REST fallback, and docs link. The REST fallback and the 'do not guess another /api/* path' note are helpful operational context. It over-delivers by restating outputs, but nothing an agent needs to invoke it correctly is missing.

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 real enum semantics: it explains that cabinet_order_330_transfers applies only to covered institutions or adopting employers and must never be inferred, and that mon_fri_planning is a required explicit baseline. This goes beyond the schema's field descriptions and helps the agent choose enum values correctly.

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 eventually conveys that the tool checks a date against the Latvia 2026 statutory calendar, weekend baseline, and transferred rest days, so the verb+resource is inferable. But it opens with a garbled, redundant phrase ('deterministic Latvia Latvia 2026 statutory calendar') that obscures rather than clarifies the purpose. It is distinguishable from the many sibling country checkers by name, but the prose itself is muddled.

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 offers a 'Use this when...' clause and a substantial 'not computed' exclusion list (six-day rosters, payroll, legal deadlines, other religious calendars), which is genuine guidance. However, the stated exclusion 'Do not use this when latvia 2026 only' is incoherent, and no sibling or alternative (e.g. count_lv_working_days, add_lv_working_days) is named, leaving usage partly implied.

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