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

Annotations already cover readOnly/idempotent/non-destructive/openWorld=false, so the bar is lower; the description still adds real behavior: deterministic output, the planning-workday formula stated explicitly, that individual leave is not deducted, and that future years need a separately verified package. It does not disclose pagination or error behavior, but those are marginal for a pure computation.

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 entry is bloated: it enumerates ~30 output fields that an existing output schema already defines, repeats the input list and JSON example already present in the schema, and contains a broken sentence ('Do not use this when malta 2026 named statutory holidays...') that reads as a fragment. The useful routing sentence is front-loaded, but a large share of the text 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?

With a rich output schema present, the description need not explain returns (though it redundantly does). It does cover the scope boundaries an agent would otherwise get wrong — leave not deducted, bank-only/school/local calendars excluded, future years needing verification — which makes it substantively complete despite the grammar problems.

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 schema already documents start_date, working_days, and work_schedule with examples, so the baseline is 3. The description restates the inputs and provides a complete JSON argument example, adding convenience but no meaning 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?

The description states a specific verb+resource: 'Adds or subtracts Malta authority-scope working days in exact coverage,' which is unambiguous. It does not, however, name its obvious siblings (check_mt_working_day, count_mt_working_days) to differentiate the offset operation from the check/count operations.

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?

'Use this when you need a deterministic Malta working-day offset' plus the instruction to call it directly rather than answering from memory gives clear usage context, and the scope exclusions (bank-only, school, local, employer, shift calendars, payroll, legal deadlines not computed) further bound it. The 'Do not use this when...' sentence is malformed and never names an alternative tool, so explicit routing to siblings is absent.

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