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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral scope: education-only November 1 does not create general rest, one-off January 2 rest, no payroll/legal-deadline computation, and a REST fallback endpoint. It does not contradict the annotations, though the formula line is terse relative to the long output list.

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 entry is bloated: it restates inputs, repeats a full JSON example that already exists in the schema, enumerates 20+ output fields even though an output schema exists, and appends REST fallback and docs URLs. The 'Do not use this when bulgaria 2026 nationwide statutory holidays, observed non-attendance days and January 2 one-off rest over an explicitly selected Monday-Friday planning baseline' sentence is garbled and unparseable, wasting prime negative-scoping space.

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 deterministic calculation tool with an output schema and full annotation coverage, the description supplies the needed scope boundaries, holiday-policy caveats, fallback endpoint, and documentation link. The broken exclusion sentence and the redundant output enumeration are flaws, but nothing critical to correct invocation is missing.

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 nevertheless adds meaning by stating that mon_fri_planning is required because it is a planning baseline rather than a universal legal roster, and by giving the planning_workday formula that defines what working_days actually counts. It also supplies a complete JSON argument example, though that largely duplicates the schema examples.

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 states a specific verb and resource: 'Adds or subtracts Bulgaria authority-scope working days in exact coverage,' and the opening line names the general behavior (deterministic Bulgaria working-day offset). It is distinguishable from sibling country variants like add_ar_working_days and from check_bg_working_day/count_bg_working_days by the add/subtract framing, though it never names those siblings explicitly.

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 Bulgaria working-day offset. Call this tool directly and return its calculation instead of answering the formula from memory' is a clear usage directive with a stated anti-pattern (relying on memory). Scope exclusions are given (no personal, shift, school, employer, bank/exchange, religious-leave, payroll, or legal-deadline schedules; future years unsupported), but no alternative sibling tool is named and the 'Do not use this when...' sentence is grammatically broken.

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