Разбивка платежей за период

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

Annotations already establish readOnlyHint and openWorldHint, but the description adds genuinely useful non-obvious behavior: counterparty is stored polymorphically in bank documents and that filter is applied in the connector, while cashflow item, purpose, period and organization are filtered server-side in 1C. That explains result differences an agent could otherwise misread. It does not discuss volume limits, performance, or how totals are computed, so it stops short of 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 first sentence front-loads the core operation and grouping, followed by a compact filter inventory and then example questions. It is dense but organized, and the final sentence on connector-vs-server filtering is high-value. The example question list is slightly redundant with the filter enumeration and could be trimmed.

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 an 11-parameter analytical read with an output schema present, the description covers the grouping dimension, the period format, all filter families, and where each filter executes. Return shape is handled by the output schema, so nothing an agent needs to call this correctly 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 description coverage is 100%, so the schema already documents every one of the 11 parameters, including accepted formats (code / name fragment / Ref_Key) and enum meanings. The description's filter list largely restates that, adding only light framing such as the period being YYYY-MM-DD and the grouping options, which the schema also carries. 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 description opens with a specific verb and resource: it sums posted bank and cash documents over a period, broken down by a chosen attribute. It enumerates the grouping dimensions (operation/month/counterparty/cashflowItem/total), so an agent knows exactly what the tool produces. It does not name the closest sibling (read.analytics.get_cashflow) or state how it differs, which keeps it from a 5.

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 is conveyed indirectly through example questions ('сколько процентов получили за год от такого-то банка', 'приход по месяцам'), which tell the agent the kind of question this answers. There is no explicit when-not guidance and no named alternative such as get_cashflow or get_purchases_breakdown for overlapping money-movement questions, so selection between siblings is left to inference.

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