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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: exactly what calendar layer is covered, what is deliberately not inferred, the dataset-refresh caveat for future annual transfer resolutions, the day-by-day formula, and a REST fallback endpoint with an anti-guessing warning. This is rich behavioral disclosure for a deterministic calculator.

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 usage trigger well and lays out inputs/outputs/formula/REST/docs in a scannable order. However the three 'Example user requests' lines are near-identical filler ('around Russia New Year's holiday / Published transfer day / Ordinary Russia working day'), and the 'Do not use this when' opener is confusingly worded, so the tightness is only adequate.

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?

With an output schema present, the description need not explain return values, yet it still enumerates them as a convenience. Combined with coverage scope, exclusions, formula, dataset-version caveat, and the REST fallback plus docs link, an agent has everything needed to invoke and trust the tool correctly.

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% — both start_date and working_days are documented in the schema, including the 'start date excluded for non-zero offsets' nuance. The description only restates the two inputs and supplies a JSON example, adding little meaning beyond the schema, so the baseline of 3 applies.

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 — 'Adds or subtracts Russia authority-scope working days in exact coverage' — and delimits the calendar scope (federal statutory/public-holiday layer plus Government-published 2026 transfer days over a Saturday-Sunday baseline). This clearly separates it from generic date tools, though it never names its closest siblings (check_ru_working_day, count_ru_working_days), so an agent must infer the add-vs-check-vs-count distinction.

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?

Opens with an explicit trigger ('Use this when you need a deterministic Russia working-day offset') and instructs the agent to call directly rather than answer from memory. The 'Do not use this when...' sentence is meant to declare scope exclusions (regional, employer, bank, school schedules are not inferred), but its phrasing is garbled and it does not route to alternative tools.

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