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

Beyond the readOnly/idempotent hints, the definition discloses real behavior: weekend defaults to the country's legal weekend, data_confidence meaning (high for fixed-date calendars, medium for lunar or overridden weekends), estimated_items naming projected dates, sources, data_version and warnings. That is a lot of operational context an agent cannot get from the annotations.

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 opening sentence is front-loaded with the verb, the convention list, and the primary use cases, so value comes first. The remainder is one very dense run-on paragraph covering calendar selection and response shape; it is efficient but slightly overstuffed for a single block.

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 10-parameter, single-required-input tool, the definition covers calendar selection paths (country vs market), subdivision, categories, weekend override, extra holidays, and the confidence semantics, so nothing needed to call it correctly is missing. An output schema exists, yet the brief confidence explanation still adds useful interpretation guidance.

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?

With 100% schema coverage the baseline is 3, and the description genuinely adds meaning on top: it explains ISDA semantics for modified_following, points to list_calendars for subdivision codes, and links include_estimated_holidays to the data_confidence flag. Minor duplication of MIC/ISO examples with the schema keeps it from a 5.

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 definition names the exact operation (apply a business-day convention to a date) and the four conventions in parentheses, and it frames the scope with concrete domains (payment, coupon, settlement, SLA dates) plus a worked example. It is unmistakable against is_working_day or add_working_days because it describes shifting a date rather than counting or testing days.

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?

The concrete use cases (payment dates, coupon dates, settlement, SLA due dates) and the 'country or market, optionally subdivided' selection rule give clear context for when the tool applies. However, it never names when to prefer it over siblings such as add_working_days, compute_deadline, or is_working_day, so the agent must infer the boundaries.

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