Дебиторская задолженность

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive behavior beyond that: results are filtered to debt > 0, credits are netted out, overdueOnly sorts descending by overdue days and falls back to 60+ day debt when no contract terms exist, and olderThanYear is explicitly flagged as often unclosed settlements rather than real debt. That fallback and caveat context is exactly what an agent needs and is nowhere in the structured fields.

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 purpose and sign convention are front-loaded, then parameter behavior follows in a logical order, with no filler sentences. It is dense and somewhat run-on as a single block, but every clause carries information rather than restating the name.

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 seven optional parameters, an output schema, and only two annotations, the description supplies the missing behavioral context — filtering, sorting, fallbacks, and data-source caveats — so an agent can call it correctly. The remaining gap is the mismatched olderThanYear reference and the absence of any pointer to the sibling payables/reconciliation tools.

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 all seven parameters are already documented; the description reinforces the meaning of aging (byAge buckets, contract payment date = document date + contract days) and the defaultTermDays 'don't guess' rule. However it also describes an `olderThanYear` parameter that does not exist in the input schema, which could lead an agent to attempt an invalid argument — a real semantic defect against an otherwise strong schema.

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 and resource — 'кто и сколько должен компании' — and pins the exact data source: сальдо счёта 62 из регистра бухгалтерии Хозрасчетный, сгруппированное по контрагентам. It also states the sign convention (debit = client debt, credit = advances, subtracted), so an agent knows precisely which figure it gets and can distinguish it from the payables sibling get_creditors.

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 clear at the parameter level: asOf for audit/historical reporting, overdueOnly for 'who is late paying', olderThanYear for long-stale balances, aging for term breakdowns. What is missing is tool-level routing — it never says when to prefer this over get_creditors, get_reconciliation, or get_unpaid_invoices, leaving that inference to the agent.

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