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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is lower, but the description still adds meaningful behavioral context: what is explicitly NOT computed (bank-only, school, local, employer and shift calendars, hours, payroll, personal entitlements, legal deadlines), that future years need a separately verified package, the exact planning formula, and a REST fallback endpoint. That is well beyond what the annotations provide.

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 purpose, but the body is bloated and partly broken: the 'Example user requests' block reads as mangled fragments ('Count Malta working days around No invented Monday compensation'), and the exhaustive Outputs list is wasted text given an output schema already exists. Several sentences do not earn their 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 single-territory count tool with an output schema, the description gives enough for correct invocation: required work_schedule enum, the planning formula, the scope exclusions and the REST fallback. Deductions only for the redundant output enumeration and the confusing fragments rather than for any missing decision-critical information.

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 schema already documents all five parameters, making 3 the baseline. The description restates the input list and provides one complete JSON argument example, and its work_schedule phrasing ('planning baseline BEFORE individual annual/compensatory leave; not personal attendance') largely duplicates the schema's own description, so little net meaning is added.

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 states a specific verb and resource ('Counts authority-scope working and non-working dates in a range') and is unambiguously scoped to Malta, which is what separates it from the ~60 sibling count_*_working_days tools. It falls short of 5 because the scoping is achieved mostly by the territory word rather than a crisp one-line statement of what distinguishes it, and the surrounding sentences are tangled.

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?

There is an explicit 'Use this when you need an auditable Malta working-day count' and a 'Call directly... instead of answering from memory' directive, which gives real usage context. However, the 'Do not use this when...' sentence is a garbled fragment that never names an alternative tool or a clean exclusion condition, so the when-not guidance is only implied.

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