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?
Adds significant behavioral context beyond annotations: multiple connections are queried sequentially with rate-limit spacing, and the return structure is `{ results, errors }` per connection. This informs the agent about performance and error handling.
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 sentences, each earning its place: the first states the core function, the second explains parameter usage, and the third covers the alternative mode. No filler or redundancy.
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?
With only one optional parameter and no output schema, the description covers all needed aspects: both usage modes, return shape, and per-connection behavior. The agent can invoke and interpret results correctly without additional information.
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 only shows `items` as a string array with no description. The description fully compensates by explaining valid selector types (item_id uuid, connector_id, or connector_name), the one-entry-per-connection rule, and the omitting behavior, providing complete semantic 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 'Lists loan contracts per bank connection' with a specific verb and resource. The description also distinguishes between listing for specific connections and all banks, making the scope explicit and differentiating from sibling tools like openfinance_get_loan_detail.
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?
Provides clear usage context: pass `items` for specific connections or omit for all linked banks. However, it does not explicitly mention alternative tools or when not to use this tool, so it lacks explicit exclusions.
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.
Each Open Finance resource has a clearly named list/get pair, and connection status vs provider status vs force sync are distinct. The main ambiguity is between list_accounts (which already carries balances) and get_account_balance, and between list_transactions and list_transactions_by_item, which requires reading the descriptions carefully.
The openfinance_* tools follow a consistent verb_noun pattern (list_*, get_*, update_*, force_sync, search_*). Exceptions like marketplace, toolkit_info, and openfinance_provider_status break the pattern slightly, but the two logical groups are predictable internally.
At 25 tools this is on the heavy end of the scale. Most tools have a real purpose, but several list/get pairs and the multi-purpose marketplace mega-tool could be consolidated without losing functionality, making the overall surface feel larger than strictly necessary.
The Open Finance surface is impressively broad: connections, accounts, balances, transactions, credit-card bills, loans, investments, categorization, sync, provider health, and connector search are all covered. Minor gaps like a single-transaction getter or a consolidated statement export force agents to assemble data with extra calls, but no critical workflow is blocked.