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?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: it queries sequentially with rate-limit spacing and returns per-connection results/errors, which is beyond the annotations. No 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?
The description is extremely concise at two sentences, front-loaded with the core purpose, and every word adds value. No redundant or extraneous 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?
Given the tool's complexity (optional filtering, no output schema), the description is complete: it covers input options, behavioral details (sequential, rate-limit), and return structure ({ results, errors } per connection). Annotations cover safety, and no additional context is needed for correct invocation.
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 only one optional array parameter with no description (0% coverage). The description fully compensates by explaining that each element is a connection selector (item_id, connector_id, or connector_name) and what happens when the parameter is omitted, adding high semantic value.
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 it lists loan contracts per bank connection, specifies the HTTP method and path (GET /loans), and distinguishes itself from siblings like openfinance_get_loan_detail by focusing on listing multiple loans rather than a single 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 guidelines on how to use the tool: pass an array of connection selectors in `items` to fetch specific connections, or omit `items` to list all linked banks. It also mentions sequential querying with rate-limit spacing, but does not explicitly compare to alternative tools like openfinance_get_loan_detail for specific use cases.
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 separated by resource (accounts, bills, loans, investments, connections), and the meta tools are distinct. The main ambiguities are openfinance_list_transactions vs openfinance_list_transactions_by_item, and openfinance_get_credit_card_bill vs openfinance_list_credit_card_bills, though their descriptions do clarify different intents.
The openfinance_* family follows a consistent verb_noun pattern, and the generic platform tools use bare lowercase names like connect, authenticate, and marketplace. The mixed prefixes and the occasional singular/plural variation (get_credit_card_bill vs list_credit_card_bills) make the overall namespace readable but not fully uniform.
25 tools is at the heavy end and combines two distinct areas: platform/meta tooling and a deep Open Finance adapter. Most openfinance tools are justifed by real endpoints, but the count feels bulky for an agent to browse, and the marketplace tool packs an unusually large number of capabilities into a single entry.
The Open Finance surface is unusually complete: accounts, balances, transactions, credit-card bills, loans, investments, connection status, force sync, provider status, category correction, and disconnect are all present. The platform side is also broad via marketplace and toolkit_info, with only minor granularity gaps such as no dedicated get-single-transaction tool or separate marketplace sub-tools.