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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety bar is lower. Beyond that, the description adds genuinely non-obvious behavior: the at-most-11-inclusive-years cap (not encoded in the schema), native-language name fallback, coverage/language metadata, and a prompt-injection warning that returned names are data rather than instructions. It still says nothing about error behavior for unsupported codes or rate limits.

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?

Three front-loaded sentences: purpose first, then the constraints and discovery pointer, then the safety/fallback caveat. Each sentence carries distinct information and nothing is repeated from the schema or annotations.

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?

With an output schema present, the description need not explain return values, and it wisely only notes the metadata signals (coverage and language). Combined with annotations this is enough to call the tool correctly. The only real gap is guidance on what happens when a country/region combination is unsupported.

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 coverage is 60%: region, country and language are documented in the schema, but startYear and endYear have no descriptions at all. The description compensates by supplying the missing constraint on the year range ('at most 11 inclusive years'), which is the key undocumented semantic. The language parameter is not addressed in the description, leaving that gap to the schema alone.

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: 'Read public holidays including observed dates.' The holiday-calendar scope is unmistakably distinct from count_days, shift_date and list_locations, and it explicitly routes code discovery to the list_locations sibling. It stops short of a full sibling differentiation sentence, so a 4 rather than a 5.

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 concrete conditions for a correct call: supply a country, an optional exact subdivision, and no more than 11 inclusive years, plus a pointer to list_locations for discovering supported codes. It does not state when NOT to use this tool or contrast it with shift_date/count_days, which keeps it out of 5 territory.

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