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?
Adds significant context beyond annotations: sequential queries with rate-limit spacing, return format as '{ results, errors }' per connection, and behavior when 'items' is omitted. No contradiction with annotations (readOnlyHint, idempotentHint, destructiveHint all consistent).
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-load the purpose and then provide usage and details. Every sentence adds value with no redundancy or wasted words.
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 no output schema, the description explains the return structure ('{ results, errors }' per connection). Does not detail the fields within results or mention pagination, but for a list tool with one parameter, this is largely complete.
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 coverage, the description fully explains the 'items' parameter: an array of connection selectors (item_id uuid, connector_id, or connector_name) and the effect of omitting it. However, it does not explicitly state the parameter is optional, though implied by schema having no required.
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 tool lists loan contracts per bank connection, specifying the endpoint 'GET /loans'. It distinguishes from sibling 'openfinance_get_loan_detail' by focusing on listing, not retrieving a single loan.
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 explicit guidance on when to pass 'items' (specific connections) and when to omit it (all banks). Does not mention when to use alternatives like 'openfinance_get_loan_detail', but the context is clear enough for typical 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.
Each tool targets a distinct resource or action: the openfinance_* family cleanly separates accounts, transactions, bills, loans, investments, connections, sync, and provider health, while platform tools (authenticate, connect, marketplace, toolkit_info) cover different concerns. Even potentially similar pairs like get_item_status vs provider_status and list_transactions vs list_transactions_by_item are clearly differentiated by their descriptions.
Open Finance tools follow a uniform openfinance_<verb>_<noun> snake_case pattern, and the generic tools are also readable English verbs/nouns (authenticate, connect, report_bug). The main inconsistency is that a few generic tools are bare nouns (marketplace, toolkit_info) while the rest are verbs, but the mix is predictable and never confusing.
25 tools sit at the upper boundary of what is comfortable, and the set spans two distinct domains (Open Finance data access plus MCP platform/marketplace management). Each tool does appear to earn its place, but the count is heavy enough to feel borderline rather than optimally scoped.
The Open Finance surface is thorough: list/get for accounts, transactions, bills, loans, and investments, with sync, connection health, provider status, category correction, and disconnect all covered. The platform side also covers authentication, connection status, marketplace discovery/invocation, bug reporting, and version info, leaving no obvious dead ends for the stated purpose.