Карточка счёта

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description still adds genuine behavioral detail: results are reconciled with the register ("сверено с регистром, consistent") and storno entries arrive as negative amounts in debit/credit — a non-obvious quirk that prevents misreading totals. It says nothing about truncation behavior when the movement count exceeds limit (default 200, max 2000), which matters for a per-movement listing.

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?

Everything is front-loaded: what the card contains, then the filters, then the investigative use cases, with no filler sentences. It is a single dense block rather than separated sections, and the enumerated output fields are somewhat verbose, but each sentence carries information an agent needs.

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 and 100% schema description coverage, the description doesn't need to restate return structure, and it wisely spends its budget on filters, accounting quirks, and investigative framing. The only real gap is the phantom documentCreatedAt parameter and the absence of any note on how limit/pagination affects completeness of the card.

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 the baseline is 3, and the description does add examples (account as "51", "62.01", "26"; dimensionRef widened to include "документ расчётов"). However it introduces documentCreatedAt, a parameter that does not exist in the input schema — an agent following the description could pass an invalid argument. That defect offsets the added examples and keeps this at baseline rather than above it.

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 concrete artifact (the account card for a period) and enumerates its contents down to the field level: date, document, content, Debit/Credit, corresponding account with analytics, running balance, opening balance, turnovers, closing balance. An agent can tell this is a per-movement ledger extract, distinct from a pure turnover summary. It stops short of naming the sibling it overlaps with (read.accounting.get_account_turnover), so it isn't 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?

It gives real investigative framing: "Для разбора: откуда остаток на 26, кто дал красное сальдо, как сложился долг", plus practical advice ("Если остаток сложился до периода — возьмите период шире") and a note that document creation time helps find entries made after month close. What's missing is explicit exclusion — it never says when to prefer get_account_turnover or get_document_postings instead.

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