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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: the exact computation formula, the 2026-2027 scope, the enumerated output fields, and a concrete REST fallback URL with a warning not to guess other paths. It stops short of auth or rate-limit details, keeping it out of the top band.

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?

Well front-loaded: purpose, exclusion, computation, example, inputs, outputs, formula, fallback, docs. The labeled structure is scannable, though the 'Inputs:' and 'Outputs:' lines duplicate the input schema and output schema respectively, so a small amount of content does not earn its place.

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 4-param, single-territory calculator this is thorough: it supplies purpose, exclusions, a worked user-request example, a full JSON argument example, the computation formula, output field names, a REST fallback with path warning, and docs. Even though an output schema exists (so returns needn't be explained), nothing an agent needs to invoke this 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 coverage is 100% and defines all four params, so the schema does the heavy lifting (baseline 3). The description goes slightly beyond by enumerating semantics inline (which dates are included, that the two booleans are optional) and providing a complete JSON argument example, adding modest clarity over 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?

'Counts national working and non-working dates in a South Africa 2026-2027 range' gives a specific verb (counts) plus resource (national working/non-working dates) plus the exact territory and date window. It cleanly separates this tool from the many count_*/check_*/add_* working-day siblings by naming the territory and the counting action.

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?

Explicitly says 'Use this when you need an auditable South Africa national working-day count' and adds a firm when-not clause excluding employer/school/bank/exchange schedules. It also instructs the agent to call it directly rather than answering from memory, which removes ambiguity about tool vs. reasoning.

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