Lists loan contracts per bank connection (GET /loans). Pass items as an array of connection selectors (item_id uuid, connector_id, or connector_name) — one entry per connection to fetch; multiple connections are queried sequentially with rate-limit spacing. OMIT items to list loans across ALL linked banks. Returns { results, errors } per connection.
| Name | Required | Description | Default |
|---|---|---|---|
| items | 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?
The description adds behavioral context beyond annotations: sequential querying with rate-limit spacing and the return format per connection ({ results, errors }). Annotations already mark it as read-only and idempotent. No contradiction is present.
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 two sentences, immediately stating the core function and then detailing parameter usage. Every sentence adds value with no redundancy or fluff. It is front-loaded and efficient.
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 no output schema, the description partially describes the return structure. It could mention potential pagination or error handling details, but for a tool with one optional parameter and a simple list operation, the description is adequately complete. The sequential behavior compensates for missing details.
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 input schema has 0% description coverage, but the description fully explains the 'items' parameter: what values it accepts (item_id uuid, connector_id, or connector_name), its behavior (one per connection), and the effect of omitting it (list all banks). This exceeds the minimum required compensation for low schema coverage.
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 lists loan contracts per bank connection, specifying the HTTP endpoint and differentiating it from sibling tools like openfinance_get_loan_detail. The verb 'list' combined with the resource 'loan contracts' and scope 'per bank connection' makes the purpose specific and unambiguous.
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 guidance on when to pass the 'items' parameter and when to omit it, including behavior for multiple connections (sequential with rate-limit spacing). It does not explicitly mention when not to use this tool (e.g., preferring a detail tool for a single loan), but the context is clear enough for most agents.
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 mostly distinct resource/action pairs, but several boundaries blur: openfinance_list_transactions vs openfinance_list_transactions_by_item vs openfinance_get_credit_card_bill(include_transactions) all return transaction data, and openfinance_get_item_status / openfinance_provider_status / openfinance_list_connections all concern connection health. The monolithic marketplace tool also bundles search/describe/invoke/install/prompt-library operations, adding further ambiguity.
The 19 openfinance_* tools follow a clean snake_case verb_noun pattern (list_accounts, get_item_status, update_transaction_category), but the six platform tools break it with bare verbs (authenticate, connect) and noun-style names (marketplace, toolkit_info). The split is namespace-based and still readable, so it is only a minor inconsistency.
25 tools is on the heavy side, but the server spans two domains: an Open Finance banking surface (accounts, bills, loans, investments, connections) and a marketplace/platform layer (auth, search, prompts, bug reporting). Many openfinance tools are necessary for that breadth, though the count is high enough to feel bloated.
The Open Finance surface is nearly complete: connections can be searched, listed, disconnected, force-synced, and health-checked; accounts, transactions, bills, loans, and investments all have read/detail paths; transaction categories can be updated. Minor gaps exist, such as no granular marketplace tools outside the monolithic marketplace tool and no single-transaction detail endpoint, but core workflows do not dead-end.