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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-structured context: the calendar scope limits, the exact output field list, dataset_version/sources provenance, and a direct REST fallback path with a warning not to guess other /api/* routes.

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?

Front-loads the core usage rule and then uses labeled sections (What it computes, Inputs, Outputs, Formula, Fallback, Docs) so an agent can scan it. It is longer than needed and includes some filler ('instead of answering the formula from memory or stopping at discovery'), and the when-not sentence is awkwardly worded.

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?

An output schema exists, so return values need not be enumerated, yet the description still lists every output field, plus the scope caveats and REST fallback. Combined with the annotations, this covers what an agent needs, though the garbled 'Do not use this when government administrative-agency scope only' line leaves a small ambiguity about the intended scope boundary.

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 would be 3; the description adds a fully populated JSON argument example plus an explicit input list, which clarifies how start/end dates and the two include_* booleans combine. It stops short of explaining the semantics of an emptied range (e.g. both includes false).

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 authority-scope working and non-working dates in a range') and pins the scope to authority/Taiwan government calendars. The scope statement partly differentiates it from add_tw_working_days and check_tw_working_day, but neither sibling is named, so the agent must infer the boundary from names alone.

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?

Gives an explicit when ('when you need an auditable Taiwan working-day count') and a detailed when-not covering special agencies, schools, private employers, banks and exchanges that are not inferred. It lacks explicit signposting to the alternative siblings (add_tw_working_days, check_tw_working_day), so it stops short of a 5.

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