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?
Annotations already provide destructiveHint=true. The description adds context: data will no longer be available and an add_connection_url is returned for reconnection. This enhances transparency beyond annotations, though it could mention irreversibility.
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 redundant words. Purpose, effect, and result are conveyed efficiently. Front-loaded with the core action.
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?
Covers the overall effect and return value, but critically omits any explanation of the required 'item' parameter. For a destructive tool with only one parameter, this gap makes it incomplete.
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 description does not mention the only parameter 'item' at all. Schema coverage is 0%, and the description fails to provide any meaning or format for the parameter, leaving the agent completely in the dark.
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 explicitly states it revokes consent and deletes connection data, with a specific verb and resource. It clearly distinguishes itself from siblings like 'connect' or 'openfinance_list_connections' by indicating a 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?
Usage is implied: use when needing to disconnect a bank. No explicit when-not or alternative tools are mentioned, though the sibling 'connect' suggests the opposite action. Guidance is minimal.
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.
Each openfinance_* tool targets a distinct resource (account, transaction, bill, loan, investment) with a clear action (get/list/update/force_sync). The administrative tools (connect, authenticate, report_bug) are clearly separate. No two tools appear to perform the same function.
The openfinance_* tools follow a consistent verb_noun pattern (e.g., get_account_balance, list_transactions, update_transaction_category). Minor deviations like openfinance_provider_status (lacks a verb) and openfinance_force_sync (verb phrase) slightly break the pattern, but the overall convention is predictable.
25 tools is on the higher end but appropriate for a comprehensive Open Finance server covering accounts, transactions, bills, loans, investments, connections, and administration. Each tool has a distinct purpose and none feel redundant.
The tool surface is complete for the domain: it covers connection management (connect/disconnect/force sync/status), account and transaction queries, credit card bills, loans, investments, and transaction categorization, plus admin utilities. No obvious gaps that would block typical workflows.