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

Annotations already cover read-only, idempotent, non-destructive, closed-world. The description adds genuinely new behavioral context: the algorithm ('move one day at a time; decrement only on status.is_working_day=true'), the deterministic guarantee, the explicit non-inference of statutory/school/bank holidays, and a REST fallback endpoint. No auth, rate-limit, or error-behavior notes, so not a 5.

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-loads the routing instruction, which is good, but the body is padded: the 16-field output list is pure duplication of the output schema, the territory name is repeated in near-identical phrasing across three lines, and the REST-fallback/docs URLs consume space without aiding selection. The useful content could be roughly halved.

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 2-parameter deterministic calculator with a full output schema and rich annotations, the description covers the remaining burden well: scope, exclusions, algorithm, and an API fallback. Enumerating return fields is redundant given the output schema, but nothing an agent needs to invoke it correctly is missing.

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 both parameters (start_date, working_days) are already documented, including the 'signed offset; start date excluded for non-zero offsets' semantics. The description repeats the input list and adds a JSON example, plus the formula clarifies what working_days means operationally, but this is marginal 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: 'Adds or subtracts 中国香港特别行政区 authority-scope working days in exact coverage', with a concrete 'What it computes' line and example requests. However, it never distinguishes itself from the many close siblings (add_china_working_days, count_hk_working_days, check_hk_working_day) or the other HK-adjacent calendars, so an agent must infer the boundary from the name alone.

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?

Gives explicit positive routing ('Use this when you need a deterministic working-day offset... return its calculation instead of answering from memory') and an explicit scope exclusion ('Do not use this when this package is the Hong Kong general/public-holiday calendar... statutory employee holidays, employer rest days, school calendars, bank/exchange closures... are not inferred'). It stops short of naming the sibling tools (count_/check_ variants) as alternatives, which is the one routing gap.

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