台灣工作日

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered; the description then adds genuinely useful context by citing the authoritative source (人事行政總處 office calendar), which tells the agent that results are tied to officially published data and its adjustment rules. The one gap is that it never states what the response looks like or what happens for dates outside the published calendar years.

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?

Two compact sentences: the first establishes what is computed and against which authority, the second encodes three usage modes in a parallel pattern. Nothing is redundant with the title, and the core purpose is front-loaded.

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 three-parameter, side-effect-free lookup tool with complete schema coverage and strong annotations, the definition covers purpose, data source, and all parameter combinations. The remaining shortfall is the absence of output format disclosure, which matters more here because there is no output schema.

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; however, the description goes beyond the field-level docs by explaining the interaction between parameters — start-only means point lookup, start+end means inclusive range counting, start+add means Nth-workday projection. The only ambiguity left is the precedence when both end and add are supplied.

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 names a specific verb (判斷/判斷 whether a date is a workday) and a specific resource (Taiwan's government-agency office calendar), and it enumerates the categories it resolves: workdays, national holidays, make-up holidays, and make-up workdays. None of the sibling tools (about, labor_overtime, lvr_search, pdf_pages, pii_mask) overlaps this niche, so the agent can route unambiguously.

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 gives explicit mode routing: start alone queries one day, adding end counts workdays across a range, adding add projects the Nth workday (the schema adds that negative values move backward). What it does not address is combining end and add at the same time, but since there is no competing tool to choose between, the guidance is clear enough.

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