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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, closed-world), but the description adds real behavioral context: the pinned 2026-2027 dataset range, the deterministic per-date formula, and a REST fallback endpoint with an explicit warning not to guess other /api/* paths. What it does not disclose is failure behavior for out-of-range dates or dataset freshness beyond the version field name.

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?

The usage and exclusion sentences are front-loaded and earn their place, but the description then enumerates ~20 output field names even though an output schema exists, which is redundant and dilutes the signal. The formula and REST/docs lines are terse and useful; the output dump is the main bloat.

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 straightforward date-range counter with a full output schema and rich annotations, the description is more than sufficient: it covers scope, exclusions, date-range limits, fallback, and docs. Its only real defect is over-explaining return values that the output schema already defines.

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 the baseline is 3; the description adds a consolidated input list with type/optionality annotations and a complete JSON argument example combining all four fields. Since the schema already carries per-field descriptions and examples, the incremental semantic value is modest but real.

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 ('Counts Türkiye statutory-baseline working and non-working dates') and pins the scope to a 2026-2027 range. It explicitly carves out what it is not (private employer, school, bank, exchange, local or collective-agreement calendars), which is the key confusion class among the many country/sector siblings. An agent can distinguish it from count_global_working_days and check_* tools from the text 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 an explicit trigger ('when you need an auditable Türkiye statutory working-day count'), an explicit exclusion ('Do not use this when you need a private employer, school, bank, exchange, local or collective-agreement calendar'), and a routing instruction to call this tool directly rather than answering from memory. This is exactly the when/when-not/alternative pattern.

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