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

Annotations already cover readOnly, idempotent and non-destructive traits, yet the description adds real value: the deterministic guarantee, the explicit scope limits (cantonal/municipal holidays not inferred), the stepwise algorithm, and a REST fallback with the exact path. This is well beyond what the annotations convey.

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?

It is front-loaded with a use/when-not/computation structure, which helps, but it is bloated and contains broken text: 'Cantonal holiday is not inferred' appears verbatim inside the example user requests, and the outputs list is long and redundant. Several sentences do not earn their place.

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 well-annotated, fully documented two-parameter calculation tool with an output schema, this is essentially complete: purpose, scope limits, inputs, algorithm, REST fallback and docs are all present. The redundant output enumeration and garbled exclusion sentence are minor blemishes, not gaps.

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 baseline is 3. The description only restates the two inputs (start_date, working_days) plus a JSON example; the schema itself carries the finer meaning (date range 2026-2027, signed offset, -1000..1000 bounds, start date excluded for non-zero offsets). No additional parameter semantics are added.

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 and resource ('Adds or subtracts Switzerland authority-scope working days in exact coverage') and scopes it to the authority/federal layer. It is clearly distinct from the many sibling country tools, though it never explicitly contrasts with its own siblings like count_ch_working_days or check_ch_working_day.

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 an explicit trigger ('when you need a deterministic Switzerland working-day offset') and instructs the agent to call it directly rather than answering from memory or stopping at discovery. It also states an exclusion (cantonal/municipal/employer/collective-agreement schedules are not inferred), though the phrase 'Do not use this when federal layer only' is garbled and hard to act on.

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