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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, but the description adds substantial behavioral context beyond them: the auditing posture, the exact computation formula, the federal-only scope limits (no provincial, bank, exchange, school, court, diplomatic calendars), how lunar festivals are pinned to 2026 notifications, and what metadata (substitute_day_policy, dataset_version, sources) is returned.

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?

It is front-loaded with the usage decision, which is good, but it is long and includes low-value sections ('Example user requests', a full outputs enumeration that duplicates the output schema, a REST fallback URL and docs link). Several sentences do not earn their place for an agent that already has the schema.

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?

Given a 4-parameter, fully-described schema and an existing output schema, the definition supplies everything an agent needs: scope caveats, when to prefer direct invocation, computation semantics, and a fallback path. Nothing required to call 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% and the description's input list (start_date, end_date, include_start_date, include_end_date) largely restates the schema. The complete JSON argument example is also already present in the schema, so added meaning is marginal; the one-line formula does clarify how the include flags drive the count.

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?

The description gives a concrete verb+resource ('Counts authority-scope working and non-working dates in a range') and an explicit 'Use this when you need an auditable Pakistan working-day count', which clearly separates it from the dozens of other country count_* siblings. It does not, however, distinguish itself from the adjacent add_pk_working_days / check_pk_working_day tools by name.

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?

It states when to use it ('auditable Pakistan working-day count', 'call this tool directly ... instead of answering the formula from memory or stopping at discovery') and provides a scope-based exclusion ('Do not use this when this package covers the nationwide federal public-holiday layer only...not a universal provincial...calendar'). No named alternative tool is offered for those excluded cases, so it stops short of a full when/when-not/alternative set.

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