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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's real added value is the coverage boundary: only authority-scope statutory days are modeled, half-day and employer-specific closures are not inferred, and Store Bededag stops being a holiday in 2024. It also exposes the computation rule ('decrement only on is_working_day=true'). This is meaningful behavioral context beyond the structured fields.

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-loaded with the use case, but bloated: it lists sixteen output fields that the output schema already defines, plus a raw REST URL and docs link, and contains some awkward phrasing ('in exact coverage', the Constitution Day example). Roughly a third of the text duplicates structured data that the agent already receives.

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 2-parameter calculator with an output schema and full annotations, the description covers the critical gaps: calendar scope, holiday policy boundary, the 2024 Store Bededag rule, an example invocation, and a REST fallback. Only the redundant output-field enumeration and the slightly malformed exclusion sentence keep it short of 5.

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 (date range, signed offset semantics, min/max). The description only restates the parameter names and gives one JSON example, adding little beyond the formula hint about one-day-at-a-time movement. Baseline 3 is appropriate.

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 Denmark authority-scope working days') and explicitly frames the tool as a deterministic offset calculator. It implicitly distinguishes itself from check_dk_working_day and count_dk_working_days via the add/subtract framing, though it never names those siblings. An agent can identify the operation 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?

Explicit 'Use this when you need a deterministic Denmark working-day offset' plus a 'Do not use this when...' exclusion listing what is out of scope (collective-agreement, employer, sector, school, bank, local, customary half-days) and the Store Bededag 2024 change. It also tells the agent to call directly rather than answer from memory, and supplies a REST fallback. The when-not sentence is slightly garbled ('nationwide statutory list only'), which keeps it from a 5.

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