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?
The description confirms the destructive hint from annotations and adds detail on what is deleted and the return of a re-connection URL. It does not contradict annotations, and provides behavioral context beyond the annotation labels.
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 only two sentences, contains no redundant information, and efficiently conveys the action and consequence.
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?
While the action is clear, the critical gap in parameter documentation makes the tool description incomplete for correct invocation. No output schema exists to compensate, and the agent needs to infer the 'item' meaning.
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?
The schema has one required parameter 'item' with zero description coverage. The description fails to explain that 'item' refers to the bank identifier or connection ID, leaving the agent without guidance on what to pass.
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 uses specific verbs ('revokes', 'deletes') and clearly identifies the resource (bank connection data). It distinguishes this tool from sibling tools like connect or list_connections by stating its destructive action.
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 clearly implies when to use it (to disconnect a bank). It does not explicitly exclude alternatives, but the context of sibling tools makes the use case unambiguous.
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 tools target distinct resources and operations (balance, accounts, loans, investments, connections, provider status), but credit card bill handling is split across three overlapping tools (get_credit_card_bill, list_credit_card_bills, list_transactions), which could cause misselection. The platform-level tools (authenticate, connect, marketplace, etc.) are clearly distinct from the finance tools.
The openfinance_* tools mostly follow a verb_noun snake_case pattern (list_accounts, get_account_balance, update_transaction_category), but a few deviate (openfinance_provider_status, openfinance_search_bank_connectors). The non-prefixed platform tools break the pattern entirely with mixed styles: verbs (connect, authenticate), nouns (marketplace), and noun_verb (report_bug, show_version).
At 25 tools, this sits at the high end of reasonable scope. Each Open Finance tool maps to a specific endpoint or workflow, and the platform tools are needed for the MCP meta-layer, but the sheer number makes the set feel heavy and harder to navigate.
The Open Finance surface is thorough: connection lifecycle, accounts, balances, transactions, credit card bills, loans, investments, categories, and provider health. Minor gaps exist (e.g., no webhook management, no bulk CSV export), but core workflows are well covered and there are no dead ends.