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?
Discloses sequential querying with rate-limit spacing and return format ({ results, errors }) beyond annotations (readOnlyHint, idempotentHint, destructiveHint). 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?
Concise, front-loaded with purpose, each sentence adds value. No 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?
Covers usage, behavior, and return format. No output schema needed; description is complete for correct tool 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?
Schema has no description for `items`; description explains it as connection selectors (uuid, connector_id, or connector_name) and omission behavior. Adds significant meaning despite 0% schema coverage.
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 the tool lists loan contracts per bank connection (GET /loans), with specific verb and resource. Distinguishes from siblings 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?
Explains when to pass `items` (for specific connections) vs omit (all banks), including sequential querying and rate-limit spacing. Does not explicitly mention alternatives but provides sufficient context.
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 and actions, but several overlap in purpose: list_transactions vs list_transactions_by_item, get_credit_card_bill vs list_credit_card_bills, and multiple connection/status tools expose reconnect URLs. The long descriptions help, but the boundaries are not always immediately obvious.
The openfinance_* tools follow a consistent list_/get_ verb_noun pattern and share a clear prefix. The smaller platform cluster is less consistent — marketplace, connect, authenticate, show_version, toolkit_info — mixing nouns, bare verbs, and snake_case, but it is a minor deviation overall.
At 25 tools, this sits at the heavy end of acceptable. The Open Finance surface is broad enough to justify many of them, but there is redundancy (e.g. list_transactions_by_item largely wraps list_transactions plus account resolution) and a separate platform-management cluster that makes the set feel sprawling.
The Open Finance domain is well covered: connection lifecycle, accounts, balances, transactions, credit-card bills, loans, investments, categories, and provider status are all present, and data flows connect properly between tools. Minor gaps exist, such as no single-transaction fetch or dedicated prompt-management tools, but the marketplace tool fills those roles.