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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds real behavioral context: the calendar is pinned to the 2027 schedule, the exact accumulation formula, the specific output fields produced, and a REST fallback URL with a warning not to guess other /api/* paths. The only gap is an explicit statement of what happens for out-of-2027 dates (implied by 'pinned 2027 schedule').

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?

Labeled sections (when-to-use, when-not, what it computes, inputs, outputs, formula, fallback, docs) front-load the decision-relevant content, so an agent can stop reading early. The one-line formula restates the obvious accumulation and the full outputs list is long, but both are defensible for an audit-oriented tool.

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 an output schema and rich annotations already present, the description still supplies the decision-critical facts an agent needs: scope (2027, Malaysian divisions), usage routing, an invocation example, and a fallback. Nothing material is missing for correct selection or invocation.

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%, so the baseline is 3; the description earns above baseline by enumerating all five inputs with types and optionality plus a complete, copy-pasteable JSON argument example that exercises the enum and both booleans. It adds practical invocation meaning rather than just restating field names.

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 working and non-working dates for a selected Malaysian division'), and the section header 'What it computes' removes any ambiguity about what the tool returns. It is distinguishable from the sibling check_my_working_day (single-day) and add_my_working_days (registration) tools by its division-scoped range-count semantics.

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?

Explicit when-to-use ('Use this when you need an auditable division-specific count... return its calculation instead of answering the formula from memory') and when-not-to-use ('Do not use this when the division is unknown or employer/sector replacement-day rules matter'). This actively steers the agent away from its default failure mode of hand-computing holidays.

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