Остатки по счетам

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

The readOnlyHint annotation already covers the safety profile, and the description adds genuinely new behavioral context: results are grouped per account currency with currency-level totals, and debts ('кто кому должен') come back in a separate 'debts' list that is excluded from the totals. It does not describe pagination or ordering, but for an aggregate read tool that is minor.

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?

Two dense sentences with the primary purpose front-loaded and the debts caveat second; no filler. It could be marginally improved by ordering the per-currency/totals detail after the debts clarification, but nothing needs to be cut.

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 no output schema and four optional parameters, the description carries the return-shape burden and does reasonably well, disclosing the per-currency grouping, currency totals, and the separate debts list. The one remaining gap is the unexplained interaction between the debts list and the subtract_debts/subtract_savings flags.

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 date, include_hidden, subtract_debts and subtract_savings are already documented in the schema; the description only echoes the default-now behavior of date. Notably it does not reconcile the stated rule that debts are excluded from totals with the existence of a subtract_debts flag, leaving a small semantic ambiguity.

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 resource and computation: 'Текущие (или на дату) остатки по счетам' broken down per account currency plus currency totals. An agent can tell this apart from list_accounts (which returns accounts, not balances), but no sibling such as get_report or list_accounts is named 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?

Usage is only implied: the parenthetical '(или на дату)' hints at the date parameter, and the note that debts are returned separately clarifies what the tool does and does not aggregate. There is no statement of when to prefer this over get_report or list_accounts, and no prerequisites or exclusions.

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