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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description adds genuinely useful behavior: Ministry of Interior precedence over secondary snapshots, lunar Eid dates subject to amendment, and the Public Holidays Act rule that no substitute day is invented for weekend holidays. The day-by-day formula disclosure is more than any annotation conveys.

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?

Usage guidance is front-loaded, which is good, but the 'Do not use this when this is the nationwide federal...' sentence is grammatically garbled and hard to parse. The enumerated Outputs list is redundant given a full output schema, and the REST fallback plus docs link pad length without aiding tool selection.

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 scoped calendar calculator with an output schema carrying return fields, the description covers what an agent needs: scope limits, holiday-precedence caveats, an argument example, and the formula. The only shortfall is the muddled when-not sentence, which slightly obscures the boundary against non-federal Nigeria calendars.

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 100%, and the schema already explains the signed offset and that the start date is excluded for non-zero offsets, so the baseline is 3. The description's 'adds or subtracts' and 'decrement only on status.is_working_day=true' reinforce the direction of the offset but add little syntax or edge-case detail beyond 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 (add/subtract Nigeria working days) and pins down the scope as the 'nationwide federal public-holiday layer' rather than a private/state/sector calendar. Against a wall of near-identical add_XX_working_days siblings, that scope qualifier is what lets an agent confirm it has the right country layer.

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 an explicit when ('you need a deterministic Nigeria working-day offset') and a when-not (not a universal private-employer/state/local/diplomatic calendar), plus a directive to call the tool directly rather than answering from memory. It never names the obvious sibling alternatives (check_ng_working_day, count_ng_working_days) for when the agent only wants a yes/no or a range count, so routing is not fully closed.

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