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

With readOnly/destructive annotations already covering safety, the description adds genuine behavioral substance: the base date is not counted (a classic off-by-one pitfall), business-day mode excludes weekends and holidays by default, and closed weekdays, obon, year-end, and per-date overrides are supported. It stops short of stating the return value or how conflicting open/closed date lists resolve.

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?

Two compact sentences lead with the core operation and mode, then add the non-obvious 'base date not counted' rule and the negative-N case. No filler, and the most decision-relevant information comes first.

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 nine-parameter date-arithmetic tool with no output schema, the description covers the behavioral model well but never says what comes back (presumably a YYYY-MM-DD string) or how holidays interact with explicit closed_weekdays/open_dates precedence. Range constraints are delegated to the schema, so the remaining gap is modest but real.

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 each of the nine parameters is already documented including ranges and defaults. The description adds only conceptual framing (business mode bundles the holiday/obon/nenmatsu/closed-weekday switches) and the negative-n convention, which is the baseline expectation when the schema does the heavy lifting.

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 operation: shifting a date forward/backward by N calendar or business days, with explicit mention of the business-day mode and negative-N reversal. This clearly separates it from siblings like count_days (measuring spans) and check_business_day (testing a single date), though it never names those alternatives explicitly.

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?

Usage is implied rather than prescribed: the parenthetical '締め切りの逆算' hints at the negative-N deadline back-calculation scenario, and 'business: true' signals when to switch modes. There is no explicit statement of when NOT to use this tool versus count_days or find_dates, leaving routing to inference.

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