MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate idempotentHint=true and destructiveHint=false, and the description complements this by explaining token usage and session behavior. It warns about token persistence. However, it could explicitly state that calling with a token modifies session state, but it's implied.
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?
Description is concise (three sentences) and structured: it starts with purpose, then best practice, then usage options. No redundant information.
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 the tool is simple with one optional parameter and no output schema, the description covers all necessary aspects: authentication flow, token options, and behavior. It is complete for an AI agent to invoke correctly.
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 description coverage is 0%, but the description fully explains the single parameter 'token': it's a JWT from browser paste, and calls can omit it to get a link. This adds significant meaning beyond the schema.
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 clearly states the tool is for authentication, detailing login via browser and token management. It distinguishes itself from sibling tools by focusing on this specific auth operation.
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?
Explicit guidance is provided: best practice is to configure a permanent token in the server config, session-only by pasting token, or calling with no args to get a login link. This covers when and how to use the tool, including an alternative.
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.
The openfinance_* tools are cleanly separated by resource and action (accounts, transactions, bills, investments, loans, connections), and the list-versus-get patterns are distinguishable. The main weak spots are the broad 'marketplace' tool, which bundles many sub-actions, and mild overlap between list_accounts/get_account_balance and list_transactions/list_transactions_by_item.
The banking tools follow a consistent openfinance_<verb>_<noun> convention, with list_/get_ prefixes used predictably. A few deviations like 'provider_status' (missing a verb) and non-prefixed platform tools (authenticate, connect, marketplace, toolkit_info) keep it from being perfectly uniform.
25 tools is on the heavy side, but the Open Finance domain justifies a wide surface: balances, transactions, bills, investments, loans, connections, sync, and provider health each need their own entry points. The platform/meta tools add some bulk but are individually useful.
The Open Finance surface covers the full read lifecycle: discover/search connectors, connect via URLs, list and inspect connections, force sync, check provider/connection status, and read accounts, balances, transactions, credit card bills, investments, and loans. It also supports the one clearly expected write operation (transaction category correction), leaving no obvious dead ends in the core domain.