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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds sequential querying with rate-limit spacing and return format '{ results, errors }', which is beyond readOnly/idempotent annotations. Still, no mention of pagination or limits.
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?
Three efficient sentences: purpose, items specification, omit behavior. No waste, front-loaded with main 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 main usage and return structure without output schema. Lacks details on pagination or error handling, but sufficient for a list tool.
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 has 0% coverage for the 'items' parameter. Description fully compensates by explaining items as connection selectors with valid types and behavior when omitted, adding critical meaning.
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?
Clearly states it lists loan contracts per bank connection with the HTTP endpoint. Distinguishes from sibling get_loan_detail by focusing on listing multiple loans per connection.
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?
Explains two modes: with items for specific connections or omit for all. Implicitly contrasts with get_loan_detail for single loans, but lacks explicit when-not or alternative references.
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 have clearly distinct purposes, especially the openfinance_* family, but there is some overlap: openfinance_list_transactions and openfinance_list_transactions_by_item both cover transaction listing (though the latter is aggregated by connection), and openfinance_get_account_balance vs openfinance_list_accounts both return balance info. Descriptions are detailed enough to guide selection, so ambiguity is limited but present.
The 19 openfinance_* tools follow a consistent verb_noun pattern (list_accounts, get_balance, force_sync). The remaining generic tools (connect, authenticate, marketplace, report_bug, etc.) don't share the prefix but use clear verb-style names. Two conventions exist, but within each group naming is predictable and readable.
25 tools is at the high end but supports the dual scope: platform management (connect, auth, marketplace) and comprehensive Open Finance data access (19 tools). The count feels slightly heavy, especially with the massive marketplace tool that bundles many actions into one, but it's justified by the breadth of the financial domain.
The Open Finance surface is quite complete: accounts, balances, transactions, bills, loans, investments, categories, connections, sync, and provider status are all covered. Missing minor operations like updating categories is present, but there is no obvious gap like missing update/delete for transactions (not applicable). The platform side is minimal but sufficient for auth and info.