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

With no annotations, the description carries the full burden and does so well: it discloses exclusion rules (weekends, Japanese holidays, and banking holidays 12/31-1/3 with calendar="banking"), the non-inclusive counting of the anchor day, and negative-direction behavior.

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 core semantics and finishing with a concrete input example. Some counting details are stated twice (anchor day not counted appears in both description and schema), but overall dense and low-waste.

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?

No output schema exists, and the description only alludes to the 'skipped' return mechanism without fully describing the response shape. For a deterministic computation tool the behavioral and parameter coverage is otherwise complete, so the gap is minor.

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 date, days, calendar, and extra_closed_dates are already fully documented in the schema. The description reinforces days/calendar behavior but adds little not already in the schema, warranting the baseline 3 for a high-coverage 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?

States a specific verb+resource: returns the date N business days from (but not counting) the given date, with explicit forward/backward semantics. It names and distinguishes itself from the sibling is_holiday, so an agent can route without opening a 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?

Explicitly routes the agent: 'if you only want to know whether date is a business day, use is_holiday instead'. It also notes days=0 yields the same info via skipped, giving clear when-to-use and when-to-use-something-else guidance.

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