Skip to main content
Glama
tossinvest-mcp

tossinvest-mcp

by scjang01

Toss Get Transactions

toss_get_transactions
Read-only

Fetch paginated account transactions—trades, transfers, FX, dividends, interest and fees—filtered by settlement date range and transaction type, with cursor paging to continue through all results.

Instructions

Account trades, transfers, FX, dividends, interest and fees (KR/US stocks, options and bonds; see assetClass). Dates use KST settlement day (expected for unsettled); omit the to filter to include future settlements. Unsettled first, newest first within each group. Follow hasNext even on empty pages; pass nextCursor unchanged and clear it if account or filters change. No order IDs.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "accountSeq": "<accountSeq>"
    },
    "name": "toss_get_transactions"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoInclusive settlement end date (KST), including future dates.
fromNoInclusive settlement start date (KST).
limitNoPage size; defaults to 10, maximum 100. Set the needed page size on the first call.
cursorNoPass nextCursor unchanged.
accountSeqYesCall toss_get_accounts first; ask the user if the intended account is unclear.
transactionTypesNoOR filter. Omit or pass an empty array for all transaction types.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.3.2
    • changedInput schema / properties / accountSeq / description
      Previous value: -"When accountSeq is required, call toss_get_accounts first. Select the user's intended account; if multiple accounts are ambiguous, ask the user."New value: +"Call toss_get_accounts first; ask the user if the intended account is unclear."
    • changedInput schema / properties / cursor / description
      Previous value: -"Opaque nextCursor from the previous response."New value: +"Pass nextCursor unchanged."
    • removedInput schema / properties / from / pattern
      Removed value: -"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$"
    • changedInput schema / properties / limit / description
      Previous value: -"Page size; defaults to 20, maximum 100."New value: +"Page size; defaults to 10, maximum 100. Set the needed page size on the first call."
    • removedInput schema / properties / to / pattern
      Removed value: -"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$"
  2. Addedv0.3.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive), and the description goes well beyond them by disclosing result ordering (unsettled first, newest first within group), the KST settlement-day semantics including future-dated settlements, and pagination behavior ('follow hasNext even on empty pages'). It does not describe the shape of individual transaction records, which is the main remaining gap.

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?

Dense, front-loaded and essentially waste-free: resource scope first, then date semantics, then ordering, then pagination rules. The telegraphic style ('No order IDs') and the dangling 'see assetClass' reference cost it a point, but every sentence carries operational information.

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

Completeness4/5

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

For a six-parameter read-only list tool with no output schema, the definition covers what an agent needs to page correctly and interpret ordering and dates. It stops short of describing returned transaction fields and flags no permission or rate-limit constraints, but nothing critical to calling it correctly is missing.

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

Parameters3/5

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

Schema coverage is 100% and already documents all six parameters, so the baseline is 3. The description adds genuine meaning for 'to' (include future settlements) and 'cursor' (unchanged, cleared on filter change), but also references an 'assetClass' selector that does not exist in the input schema, which can send an agent looking for a nonexistent parameter.

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

Purpose4/5

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

The opening clause enumerates the exact resource: account trades, transfers, FX, dividends, interest and fees across KR/US stocks, options and bonds. An agent can distinguish this from toss_get_orders (explicitly excluded via 'No order IDs') and from toss_get_trades, though the latter distinction is left implicit rather than named.

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

Usage Guidelines3/5

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

Usage guidance is present but operational rather than comparative: it explains the settlement-date filtering model, the omit-'to' behavior, and strict cursor discipline ('pass nextCursor unchanged and clear it if account or filters change'). There is no explicit statement of when to choose this over toss_get_trades or toss_get_orders, so sibling selection is only inferable.

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