group_byGroup transactions by a dimension (month/category/merchant/account/currency) and apply a metric to each group. Results are per-currency. Scope defaults to all your completed statements; pass "scope" to narrow to specific accounts/products and/or a date range.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | ||
| filter | No | ||
| metric | Yes | ||
| dimension | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| scope | Yes | ||
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description adds value by disclosing that results are per-currency and scope defaults to completed statements, which are behavioral details beyond the safety annotations. No contradictions were found.
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 two sentences, front-loaded with the core action, and uses minimal words to convey essential information. It is well-structured and easy to parse.
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 complexity (nested scope object, filter with many subfields, 4 parameters, output schema present), the description is insufficient. It does not mention the filter parameter at all, nor does it explain the relationship between scope and filter, leaving significant gaps for an agent to correctly invoke the tool.
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 coverage is 0%, meaning the description should compensate by explaining parameters. It only mentions 'scope' and the enum values for dimension/metric are self-explanatory, but it completely omits the 'filter' object and its many fields, leaving agents without guidance on using filtering capabilities.
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 groups transactions by a listed dimension (month/category/merchant/account/currency) and applies a metric, distinguishing it from sibling tools like time_series or aggregate by explicitly mentioning the grouping dimensions and per-currency results.
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?
It provides clear context on default scope (all completed statements) and how to narrow it via the 'scope' parameter, but does not explicitly contrast with alternative tools or state when not to use it. This is adequate but not comprehensive.
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.
Core tools are cleanly separated by resource: statements, transactions, transfers, credits, and benchmark all have dedicated entry points. The five analytics tools (aggregate, group_by, compare, time_series, top_n) share metric/filter language, but their distinct output shapes and careful descriptions prevent major confusion, with only group_by vs. time_series/top_n occasionally overlapping.
Most tools follow a clear snake_case verb_noun pattern such as convert_statement, list_transactions, rate_statement, and dismiss_statement. The analytics tools (aggregate, compare, group_by, time_series, top_n) break that pattern, but they are still recognizable, consistently styled, and form a meaningful cluster.
At 16 tools, this is slightly above the typical 3-15 well-scoped range, but the server covers a broad workflow: upload, conversion, retrieval, categorization, analytics, transfer matching, rating, credits, and benchmarking. Each tool maps to a distinct capability, so the count feels justified rather than bloated.
The tool surface covers the full statement lifecycle from upload and conversion through retrieval, categorization, analysis, rating, and dismissal, plus useful side capabilities like credits and benchmark evaluation. Minor gaps exist—no permanent deletion and no way to manually edit category mappings—but dismiss_statement and categorize_statement provide adequate workarounds.