Уплаченные налоги и взносы за период

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful domain behavior beyond that: it discloses the exact detection criterion (bank debits with a specific ВидОперации) and thereby its inherent limitation — only bank-executed tax payments are counted, not accruals. It does not cover empty-result behavior or whether untranslated/unmatched taxes are excluded, keeping it below a 5.

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 definition is front-loaded: the core measurement rule and its rationale come first, followed by grouping, parameter hints, and example questions. Some parenthetical asides (the long enumeration of tax types and the «в БП 3.0» justification) are dense but each earns its place by justifying the marker's reliability.

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, return values need no explanation, and the description still supplies period format, database defaulting, organization filter scope, and grouping semantics. The main gaps are the groupBy default mismatch and no mention of currency or what an empty/non-matching period yields — small but real for a financial aggregate.

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 is 3. The description does add value for cashflowItem by giving concrete tax-type examples («УСН», «Страховые», «НДФЛ», «ЕНП») and matches the groupBy breakdown options. However, it states the default output is «итог», while the schema declares groupBy default = "cashflowItem" — this discrepancy could cause the agent to mis-predict the default response shape.

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 names a specific verb+resource (sum of paid taxes/insurance contributions for a period) and pins down the exact data source — outgoing bank debits with ВидОперации=«ПеречислениеНалога». It enumerates the covered tax types (ЕНП, НДФЛ, страховые взносы, УСН/ПСН, налог на прибыль), so an agent can distinguish it from generic siblings like get_cashflow or get_payments_breakdown without opening the schema.

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?

Usage context is clear and reinforced with concrete example questions («сколько налогов мы заплатили в прошлом году», «помесячная нагрузка»), plus the default mode (total) vs. breakdown mode. What is missing is an explicit negative boundary — it never names an alternative tool for total outgoing payments or states when NOT to use this one, so the agent must infer the routing.

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