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?
Annotations indicate readOnly and non-destructive; description adds GET method, return structure { results, errors }, and concurrency behavior (sequential spacing). No contradictions.
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?
Two sentences, front-loaded purpose, efficient parameter details. No redundancy or unnecessary information.
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 no output schema, description includes return structure. Could specify format of results/errors, but sufficient for simple list tool given annotations.
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?
Only parameter `items` is described in detail: array of connection selectors (item_id, connector_id, or connector_name), one per connection. Schema coverage is 0%, so description provides essential 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?
The description clearly states 'Lists loan contracts per bank connection' with the API endpoint, and distinguishes from siblings like openfinance_get_loan_detail by specifying the scope (per connection vs. single item).
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?
Explicit guidance: pass `items` for specific connections or omit for all banks, with behavior for multiple connections (sequential with rate-limit spacing). Helps agent decide when to use.
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_* family is cleanly separated by resource and action, and tricky pairs like list_accounts vs get_account_balance and list_transactions vs list_transactions_by_item are explicitly cross-referenced in descriptions. However, marketplace bundles a large set of sub-actions, and connect/toolkit_info partially overlap on reporting connection state, so a couple of boundaries are fuzzy.
The openfinance_* tools consistently follow a verb_resource pattern with snake_case, which is highly predictable. The generic platform tools mostly fit the same style, but marketplace and toolkit_info are noun-only names, and openfinance_provider_status also breaks the verb pattern, so it is not perfectly uniform.
At 25 tools, this server falls at the heavy end of the borderline range. The many openfinance_* list/get tools are individually justified for the financial domain, but adding platform tools like marketplace, connect, toolkit_info, and show_version makes the overall surface larger than a minimal server needs.
The financial surface is remarkably thorough: accounts, transactions, credit card bills, loans, investments, categories, connection lifecycle, sync, and provider health are all covered with list/get and update paths where applicable. The platform side also covers auth, connection status, marketplace discovery/execution, versioning, and bug reporting, leaving no obvious dead ends.