Revokes the Open Finance consent for a specific bank and deletes the connection data. The bank's data will no longer be available. Returns an add_connection_url to re-connect if needed.
| Name | Required | Description | Default |
|---|---|---|---|
| item | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses destructive nature (deleting data) and provides useful info beyond annotations: returns reconnection URL. No contradictions with annotations.
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?
Two sentences, no fluff. Front-loaded with the main action, succinctly covers purpose and outcome.
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?
Given tool simplicity (1 param, no output schema), description covers what happens and return value. Missing parameter description prevents a 5.
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 0% and description does not explain the 'item' parameter. The description says 'for a specific bank' but does not link it to the parameter, leaving ambiguity.
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?
Description clearly states the action: revokes consent and deletes connection data. It specifies the resource (specific bank) and distinguishes from sibling tools like 'connect' or listing tools.
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?
Implies when to use (to disconnect a bank) but no explicit guidance on when not to use or prerequisites (e.g., connection must exist). Alternatives like 'connect' are implied but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most openfinance_* tools target distinct resource/action pairs, but there is real overlap among list_accounts, get_accounts_detail, and get_account_balance, as well as between list_transactions and list_transactions_by_item, and between get_credit_card_bill and list_credit_card_bills. The descriptions are detailed enough to usually resolve ambiguity, but the number of near-overlapping read/status tools makes mis-selection plausible.
The 21 openfinance_* tools follow a clear openfinance_<verb>_<noun> convention with predictable verbs like list, get, update, force, disconnect, and search. The non-prefixed platform tools (authenticate, connect, marketlace, report_bug, show_version, toolkit_info) break the pattern but are few enough to keep the naming mostly coherent.
25 tools is at the heavy end for the stated banking domain, and several could reasonably be merged: get_account_balance/get_accounts_detail/list_accounts and list_transactions/list_transactions_by_item overlap in purpose. The breadth of resources covered accounts, cards, loans, investments, connections, and provider health helps justify the count, but it still feels slightly bloated.
The Open Finance workflow is thoroughly covered: connect discover, force sync, status checks, accounts, balances, transactions, credit-card bills, loans, investments, category correction, disconnection, and provider health. Edge cases like stale data, consent errors, provider incidents, and cross-connector asymmetries are explicitly handled, leaving no obvious dead ends for an agent.