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 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate idempotentHint=true, no destructive/read-only. Description adds behavioral context: calling with no args returns a link, with token performs login. It explains the two distinct behaviors (config vs session) and implies no side effects beyond authentication state. 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?
The description is front-loaded with purpose and usage, then details the two modes. While slightly long, every sentence adds value—no redundancy. Structure is logical and efficient for the tool's complexity.
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's simplicity (1 optional param, no output schema), the description covers all key aspects: purpose, two usage modes, best practice. It could mention expected response format, but this is minor. Overall sufficient for an agent to use 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 coverage is 0%, so description must explain the single parameter 'token'. It does so clearly: optional, when provided logs in, when omitted returns login link. This adds essential meaning beyond the schema's type definition.
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's purpose: authentication via an access token, with two modes (permanent config vs session token). It distinguishes between calling with no args (get link) and with token (login). The verb 'authenticate' and resource 'access token' are explicit, and the description differentiates this tool from siblings by focusing on login/token management.
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 provides explicit when-to-use guidance: for initial login, either by adding token to config (recommended permanent) or pasting token for session. It mentions the alternative of config-based approach as 'best'. However, it does not contrast with sibling tools like 'connect' or explicitly state when not to use this tool.
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 are clearly separated by resource and action, and the long descriptions help, but several pairs can trip up an agent: authenticate/connect both deal with login/connection state, openfinance_list_transactions and openfinance_list_transactions_by_item sound nearly identical, and marketplace internally exposes report_bug/list_tools functions that also exist as top-level tools. This is more than a single ambiguous edge.
The 19 openfinance_* tools follow a clean get_/list_/update_ pattern and are easy to navigate, but the platform-level tools break the convention: authenticate, connect, marketplace, toolkit_info, report_bug, and show_version mix bare verbs, nouns, and noun-noun compounds. The pattern is not chaotic, but it is definitely mixed.
25 tools is on the heavy end of the borderline range and is a large working set for an agent. The openfinance tools are individually justified and support batching, but the extra platform/marketplace tools add scope and some redundancy with report_bug and toolkit_info.
For a bank-data aggregation server, the surface is complete: connector discovery, linking/reconnecting/disconnecting, account lists and details, balances, transactions, categorization, credit-card bills, investments, loans, sync status, and provider health are all covered. There are no obvious dead ends in the main workflows.