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 real value beyond that: the deterministic full-coverage claim, the exact authority-event basis, the explicit statement that sub-national and sector calendars are NOT inferred, and the warning that future annual calendars 'require refreshed official evidence'. This is well above the annotation-only baseline.

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 and every block (when, when-not, what it computes, examples, inputs, outputs, formula, fallback, docs) is labeled, so navigation is easy. However it is padded: the 'Colombia Colombia' duplication, '2026-2026', the enumerated output field list that duplicates the output schema, and the REST fallback/docs URLs add bulk without helping tool selection.

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 the returned-field list is redundant but harmless, and the description need not explain the return structure. What it does supply well is the coverage boundary (nationwide statutory layer only, no sub-national inference, 2026 window) that an agent needs to avoid over-claiming results. Only the numeric-year typo and lack of explicit sibling routing keep it short of complete.

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?

There is a single required parameter with 100% schema description coverage, so the schema already documents the Gregorian date input and the baseline is 3. The description restates the input name and gives three complete JSON argument examples, which is mild reinforcement rather than new semantic content (no format, timezone, or range guidance beyond what the schema says).

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 gives a specific verb+resource ('Checks a date against the Saturday-Sunday weekend baseline and exact 2026 authority events') and scopes it to Colombia's nationwide statutory paid-rest layer, which is enough to separate it from the add_*/count_* siblings in principle. It never names a sibling explicitly, and the header sentence is marred by the duplicated 'Colombia Colombia' and '2026-2026', but the core purpose is unambiguous.

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 ... result. Call this tool directly and return its calculation instead of answering the formula from memory' gives clear positive framing, and the 'Do not use this when' block states the exclusions (municipal, departmental, school, bank, employer, sector, local patron-saint schedules). No alternative sibling tool is named, so routing to count_co_working_days or add_co_working_days is left to inference, but the when/when-not coverage is strong.

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