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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description goes further by disclosing determinism, the exact coverage window (2026-2027), the weekend baseline rule, explicit scope exclusions, and a REST fallback URL — real behavioral context beyond 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?

Front-loaded with the when-to-use trigger, but the body is padded with a garbled 'Do not use' sentence, duplicated example requests, an explicit outputs list (already in the output schema), a formula, a REST fallback and a docs link. Every field earns some place, but the hedging and redundant 'Inputs/Outputs/Formula' sections dilute it.

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 single-param deterministic calendar check with an output schema, annotations and a docs link, the description supplies coverage window, exclusions and determinism guidance — nearly everything an agent needs. The contradictory 'Do not use this when...' line is the one gap that could mislead an agent about applicability.

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?

Only one parameter with 100% schema description coverage, so the schema already documents it and the baseline is 3. The description adds the coverage-window constraint ('pinned Hong Kong Government 2026-2027') and concrete JSON examples, which is marginal added value over the 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 and resource: checks a date against the Sunday weekend baseline and exact 2026-2027 authority events for the Hong Kong general-holiday calendar. It scopes the calendar ('government/general public calendar only'), which helps separate it from the many check_*_working_day siblings, though it never names the closest siblings (add_hk_working_days, count_hk_working_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?

Provides a use-when trigger ('you need a deterministic ... result') and a directive to call it rather than answer from memory, plus a list of what is NOT covered (statutory employee holidays, employer rest days, school/bank/exchange closures). However, the 'Do not use this when this package is the Hong Kong general/public-holiday calendar' clause is self-contradictory and confusing, and no sibling alternative (add_hk_working_days vs check_ vs count_) is ever named.

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