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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds substantive domain behavior beyond them: sixteen statutory holidays, conditional one-hour eve markers never adding full-day rest, no weekend substitution or bridge inference, and that work_schedule selects a planning calendar rather than a universal roster. That is genuine added context.

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 description is bloated and repetitive (duplicated 'Lithuania Lithuania', lower-cased 'lithuania 2026 Labour Code'), with eight literal JSON argument examples and a full output-field list that duplicate the schema and output schema. The most important routing guidance is buried and mangled rather than 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 calendar-rule tool the description does cover scope limits, holiday counting rules, and the planning-vs-personal distinction, and an output schema exists so return values need not be explained. But the contradictory 'do not use' line and the garbled opening undermine reliability, leaving the agent with an unclear selection story.

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% with only two parameters, so the schema itself documents date and work_schedule (including the enum meaning). The description restates the enum choices and clarifies the calendar is a baseline, not a personal roster, but adds little beyond what the schema already says; baseline 3 is appropriate.

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 name and later prose establish it checks whether a single date is a working day in the Lithuania 2026 five- or six-day planning week, and the formula line confirms that. However the opening sentence is garbled ('Lithuania Lithuania 2026 statutory holiday facts over explicit mon_fri_planning result') and it never distinguishes itself from check_lv/check_ee or from its own count_lt_working_days and add_lt_working_days siblings.

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?

The 'Do not use this when lithuania 2026 Labour Code holiday facts with explicit mon_fri_planning or mon_sat_planning' line is incoherent and arguably tells the agent not to use the tool in exactly the case it exists for, which is actively misleading. There is some useful scope exclusion (hours, pay, shifts, local/employer rosters, deadlines, future years are not computed), but the primary when/when-not guidance is broken.

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