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?
Discloses sequential querying and rate-limit spacing, plus the return structure `{ results, errors }`. Annotations already indicate readOnly and idempotent, so description adds non-obvious behavior without contradiction.
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 highly informative sentences with no redundancy, front-loaded with the main action and endpoint.
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 parameter usage, behavior for single vs. multiple connections, and return structure. No output schema exists, but description provides sufficient context for a list tool with one parameter.
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?
With 0% schema description coverage, the description fully explains the only parameter `items`: it's an array of connection selectors (item_id uuid, connector_id, or connector_name), and how omitting it lists all banks.
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 verb 'list' and resource 'loan contracts per bank connection', and distinguishes itself from sibling tools like openfinance_get_loan_detail by specifying scope (per connection or all).
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?
Explicitly explains when to use `items` vs. omit it, and mentions rate-limit spacing for multiple connections. However, does not contrast with alternatives like openfinance_get_loan_detail for single loan retrieval.
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 target distinct resources (accounts, transactions, bills, loans, investments, connections, categories), so the core surface is clearly separated. However, several pairs could be confused at first glance: list_transactions vs list_transactions_by_item (both return transactions but at different scopes), get_credit_card_bill vs list_credit_card_bills (bill detail vs list of bills), and get_account_balance vs get_accounts_detail (balance snapshot vs full account object). The detailed descriptions help, but the overlap is nontrivial.
The openfinance_* tools follow a consistent pattern (list_, get_, update_, search_, force_sync, provider_status, disconnect_bank), all using snake_case with a clear domain prefix. However, the general platform tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) have no such prefix or consistent verb_noun pattern, mixing the convention. The finance subset is strong, but the overall set isn't uniform.
At 25 tools, this is at the upper boundary of acceptable for a broad financial domain covering connections, accounts, transactions, credit cards, loans, investments, categories, and provider health. Each tool adds real capability, so it doesn't feel bloated, but it's heavier than typical and pushes the borderline between well-scoped and too many.
The surface covers the Open Finance lifecycle thoroughly: connection management (list, reconnect, force sync, disconnect, provider status), account/balance reads, transaction listing (with filters, pagination, rich detail), credit card bills (closed and open/debt), loans, investments, category management, and a connector search. Obvious gaps like a tool for creating connections are handled via widget URLs rather than an API call, so the coverage feels adequate. Minor gaps exist (e.g., no explicit tool for updating a connection's credentials beyond reconnect URLs), but nothing that would block core workflows.