report__get_customer_transactions_by_date

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

With annotations already declaring readOnlyHint=true and destructiveHint=false, the safety profile is covered. The description adds meaningful behavior beyond annotations: dates are interpreted as UTC-inclusive, the response is paginated, and the MCP server throttles at 10 requests/60s with an explicit caching recommendation. This is exactly the kind of operational context annotations do not provide. No contradiction with the read-only hint.

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 description is compact at roughly four sentences, but structurally messy: the 'Returns:' line runs directly into the ID-sourcing note and throttling advice in a single run-on paragraph. The Args/Returns docstring format fights with the prose instructions. Every sentence earns its place, but the organization hurts scannability.

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 a tool with a complex nested request and no output schema, the description covers the input side well (period, pagination, UTC semantics, ID sources, throttling). But it omits response shape details beyond 'list of transactions' — a real gap given no output schema exists — and it never addresses the by_revision alternative. Adequate but a capable agent would still need to inspect sibling tools or guess at the expected answer.

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 0% for the top-level 'request' parameter, so the description must compensate. It partially does by grouping the request contents as customer/organization, period, and pagination, and by clarifying date semantics. However, it leaves per-field details (zero-based pageNumber, pageSize cap behavior, uuid formats) to the nested $def, which only documents four of the six fields. The description bridges the gap but does not fully carry parameter semantics.

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+resource+scope: 'Получить транзакции клиента за период (постранично)' (get customer transactions for a period, paginated). This clearly states what the tool does and its period-based, paginated nature. It does not explicitly name the closest sibling report__get_customer_transactions_by_revision, though the tool name itself carries the 'by_date' vs 'by_revision' differentiation.

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?

The description provides solid operational prerequisites: where to obtain customerId (customers__get_customer_info) and organizationId (organizations__get_organizations), plus a caching directive for the 10-per-60s MCP throttle. However, it gives no guidance on when to choose this date-based tool versus the sibling report__get_customer_transactions_by_revision — the most relevant alternative an agent would need to disambiguate between.

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