Skip to main content
Glama
T-Bank Invest MCP Server (read-only)

T-Bank Invest MCP Server (read-only)

by Sicness

get_operations

Read-only

Fetch transaction history for a T-Bank account by date range, with optional state or instrument filters. Returns buys, sells, dividends, taxes, deposits, and withdrawals.

Instructions

Get list of operations (transactions) for an account within a date range.

Returns: buys, sells, dividends, coupons, taxes, commissions, deposits, withdrawals, etc. Each operation has: id, operationType (the code, e.g. OPERATION_TYPE_BUY), type (the same in Russian words), date, state, payment, price, quantity, quantityRest, figi, instrumentUid, positionUid, trades. A field that is zero or empty is left out; assetUid is left out too.

Canceled orders are operations as well, and carry the quantity and the payment they asked for: pass state="EXECUTED" before adding up money or quantities. quantity is what the order asked for and quantityRest what was not executed, so the executed quantity is their difference. A bond repayment has no quantity. Prices and quantities are as they were at the time: unlike candles, they are not adjusted for later splits.

Note: this method has no paging. An operation is about 450 characters, so about 100 of them fit into a client's limit, and a month of an active account can be twice that — keep the range to a week or two, or use get_operations_by_cursor, which pages. The API returns no more than 1000 operations, the latest ones; when that happens the result starts with a "note" saying so, and the earlier operations are not in it.

Args: account_id: Account ID from_date: Start date (YYYY-MM-DD), default: 14 days ago — about as much as a client's limit takes for an active account to_date: End date (YYYY-MM-DD, inclusive), default: now state: Filter by state: EXECUTED, CANCELED, PROGRESS (empty = all) figi: Filter by instrument — FIGI, ticker, ISIN or UID (empty = all instruments)

Input Schema

NameRequiredDescriptionDefault
figiNo
stateNo
to_dateNo
from_dateNo
account_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only give readOnlyHint and openWorldHint, and the description goes well beyond them: no paging, a hard 1000-operation truncation surfaced via a leading "note", zero/empty fields omitted, canceled orders included in results, prices unadjusted for splits, and quantity vs quantityRest semantics. This is unusually rich behavioral disclosure for a read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core purpose, then the return shape, then caveats, then the args list — a logical order with no filler sentences. It is on the long side and a few clauses (e.g. the split-adjustment aside) could be tightened, but almost every sentence carries decision-relevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-param tool with no output schema and no meaningful parameter documentation in the schema, the description supplies everything needed: return field list, truncation behavior, filter semantics, and the paging escape hatch to the sibling tool. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the full burden, and it does: every one of the 5 params is documented with format (YYYY-MM-DD), defaults (14 days ago / now), inclusive semantics for to_date, the full enum for state, and the non-obvious fact that figi also accepts ticker, ISIN or UID.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Get list of operations (transactions) for an account within a date range") and enumerates exactly what kinds of records come back. An agent can distinguish it from the sibling get_operations_by_cursor purely from the description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative (get_operations_by_cursor) and the condition that selects it (paging needed / range longer than a week or two). It also warns to pass state="EXECUTED" before summing money and quantities, and that the 1000-operation cap silently drops older data — all actionable when-to-use guidance.

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