Skip to main content
Glama

Bankstatemently

by io.github.bankstatemently

Aggregate Transactions

aggregate
Read-only

Compute a single metric (sum/average/count/max/min) over a filtered set of transactions across your converted statements. Results are per-currency — never sum across currencies yourself. Scope defaults to all your completed statements; pass "scope" to narrow to specific accounts/products and/or a date range. For "how many credits do I have" / processing quota / remaining pages, use get_credits instead — that is not a transaction.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scopeNoOptional structural scope (WHO × WHEN). Omit to search across all your completed statements. "accounts" is a list of account/product chips (kind + identityKey); "dateRange" bounds by transaction date (YYYY-MM-DD).
filterNoSubset of transactions to operate on. All fields are optional and combined with AND logic.
metricYesAggregation metric.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
scopeYes
resultYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed21 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / properties / filter / description
      Added value: +"Subset of transactions to operate on. All fields are optional and combined with AND logic."
    • addedInput schema / properties / filter / properties / accounts / description
      Added value: +"Account number slugs to include."
    • addedInput schema / properties / filter / properties / amountMax / description
      Added value: +"Inclusive maximum absolute amount."
    • addedInput schema / properties / filter / properties / amountMin / description
      Added value: +"Inclusive minimum absolute amount."
    • addedInput schema / properties / filter / properties / category / description
      Added value: +"Category slug, e.g. \"meals_entertainment\", \"groceries_personal\"."
    • addedInput schema / properties / filter / properties / currency / description
      Added value: +"ISO 4217 currency code. E.g. \"USD\", \"HKD\"."
    • addedInput schema / properties / filter / properties / dateEnd / description
      Added value: +"ISO date (YYYY-MM-DD). Inclusive upper bound."
    • addedInput schema / properties / filter / properties / dateStart / description
      Added value: +"ISO date (YYYY-MM-DD). Inclusive lower bound."
    • addedInput schema / properties / filter / properties / direction / description
      Added value: +"Semantic direction."
    • addedInput schema / properties / filter / properties / merchant / description
      Added value: +"Substring match against description or counterparty (case-insensitive)."
    • addedInput schema / properties / filter / properties / text / description
      Added value: +"Whole-row text search over raw transaction fields (case-insensitive)."
    • addedInput schema / properties / metric / description
      Added value: +"Aggregation metric."
    • addedInput schema / properties / scope / description
      Added value: +"Optional structural scope (WHO × WHEN). Omit to search across all your completed statements. \"accounts\" is a list of account/product chips (kind + identityKey); \"dateRange\" bounds by transaction date (YYYY-MM-DD)."
    • addedInput schema / properties / scope / properties / accounts / description
      Added value: +"Account/product chips (kind + identityKey) to scope to. Empty = all accounts."
    • removedInput schema / properties / scope / properties / accounts / items / anyOf
      Removed value: -[
-  {
-    "properties": {
-      "anchorContentHash": {
-        "type": "string"
-      },
-      "identityKey": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "account",
-        "type": "string"
-      },
-      "label": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "identityKey"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "identityKey": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "product",
-        "type": "string"
-      },
-      "label": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "identityKey"
-    ],
-    "type": "object"
-  }
-]
    • addedInput schema / properties / scope / properties / accounts / items / oneOf
      Added value: +[
+  {
+    "properties": {
+      "anchorContentHash": {
+        "description": "Document-anchored lookup when present (results page); omit for a user-scoped lookup (workspace surfaces).",
+        "type": "string"
+      },
+      "identityKey": {
+        "description": "Canonical account identity key (accountIdentityKey), never a raw DB UUID.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "kind": {
+        "const": "account",
+        "description": "This chip addresses a single account.",
+        "type": "string"
+      },
+      "label": {
+        "description": "Display label for this chip.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "identityKey"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "identityKey": {
+        "description": "Product slug.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "kind": {
+        "const": "product",
+        "description": "This chip addresses a product and expands to its child accounts.",
+        "type": "string"
+      },
+      "label": {
+        "description": "Display label for this chip.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "identityKey"
+    ],
+    "type": "object"
+  }
+]
    • addedInput schema / properties / scope / properties / dateRange / description
      Added value: +"Bounds results to transactions within this date range. Omit for no date filter."
    • addedInput schema / properties / scope / properties / dateRange / properties / from / description
      Added value: +"Start of the date range (inclusive), YYYY-MM-DD."
    • addedInput schema / properties / scope / properties / dateRange / properties / to / description
      Added value: +"End of the date range (inclusive), YYYY-MM-DD."
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed19 schema fields changed
    • removedInput schema / properties / filter / description
      Removed value: -"Subset of transactions to operate on. All fields are optional and combined with AND logic."
    • removedInput schema / properties / filter / properties / accounts / description
      Removed value: -"Account number slugs to include."
    • removedInput schema / properties / filter / properties / amountMax / description
      Removed value: -"Inclusive maximum absolute amount."
    • removedInput schema / properties / filter / properties / amountMin / description
      Removed value: -"Inclusive minimum absolute amount."
    • removedInput schema / properties / filter / properties / category / description
      Removed value: -"Category slug, e.g. \"meals_entertainment\", \"groceries_personal\"."
    • removedInput schema / properties / filter / properties / currency / description
      Removed value: -"ISO 4217 currency code. E.g. \"USD\", \"HKD\"."
    • removedInput schema / properties / filter / properties / dateEnd / description
      Removed value: -"ISO date (YYYY-MM-DD). Inclusive upper bound."
    • removedInput schema / properties / filter / properties / dateStart / description
      Removed value: -"ISO date (YYYY-MM-DD). Inclusive lower bound."
    • removedInput schema / properties / filter / properties / direction / description
      Removed value: -"Semantic direction."
    • removedInput schema / properties / filter / properties / merchant / description
      Removed value: -"Substring match against description or counterparty (case-insensitive)."
    • removedInput schema / properties / filter / properties / text / description
      Removed value: -"Whole-row text search over raw transaction fields (case-insensitive)."
    • removedInput schema / properties / metric / description
      Removed value: -"Aggregation metric."
    • removedInput schema / properties / scope / description
      Removed value: -"Optional structural scope (WHO × WHEN). Omit to search across all your completed statements. \"accounts\" is a list of account/product chips (kind + identityKey); \"dateRange\" bounds by transaction date (YYYY-MM-DD)."
    • removedInput schema / properties / scope / properties / accounts / description
      Removed value: -"Account/product chips (kind + identityKey) to scope to. Empty = all accounts."
    • addedInput schema / properties / scope / properties / accounts / items / anyOf
      Added value: +[
+  {
+    "properties": {
+      "anchorContentHash": {
+        "type": "string"
+      },
+      "identityKey": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "kind": {
+        "const": "account",
+        "type": "string"
+      },
+      "label": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "identityKey"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "identityKey": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "kind": {
+        "const": "product",
+        "type": "string"
+      },
+      "label": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "identityKey"
+    ],
+    "type": "object"
+  }
+]
    • removedInput schema / properties / scope / properties / accounts / items / oneOf
      Removed value: -[
-  {
-    "properties": {
-      "anchorContentHash": {
-        "description": "Document-anchored lookup when present (results page); omit for a user-scoped lookup (workspace surfaces).",
-        "type": "string"
-      },
-      "identityKey": {
-        "description": "Canonical account identity key (accountIdentityKey), never a raw DB UUID.",
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "account",
-        "description": "This chip addresses a single account.",
-        "type": "string"
-      },
-      "label": {
-        "description": "Display label for this chip.",
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "identityKey"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "identityKey": {
-        "description": "Product slug.",
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "product",
-        "description": "This chip addresses a product and expands to its child accounts.",
-        "type": "string"
-      },
-      "label": {
-        "description": "Display label for this chip.",
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "identityKey"
-    ],
-    "type": "object"
-  }
-]
    • removedInput schema / properties / scope / properties / dateRange / description
      Removed value: -"Bounds results to transactions within this date range. Omit for no date filter."
    • removedInput schema / properties / scope / properties / dateRange / properties / from / description
      Removed value: -"Start of the date range (inclusive), YYYY-MM-DD."
    • removedInput schema / properties / scope / properties / dateRange / properties / to / description
      Removed value: -"End of the date range (inclusive), YYYY-MM-DD."
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the operation read-only and non-destructive, so the bar for behavioral disclosure is lower. The description adds valuable behavioral context beyond annotations: results are per-currency and must not be summed across currencies, and the scope defaults to all completed statements. This is meaningful operational guidance that the annotations alone do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loads the core action, and avoids redundancy. Each sentence earns its place: the operation, the critical per-currency caveat, the scope default, and the sibling-tool routing. There is zero filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return-value explanation is unnecessary, and the input schema is rich. The description supplies the key contextual pieces: default scope, scope narrowing options, and the get_credits exclusion. It could go slightly further by clarifying how scope and filter relate to each other, but overall the agent has enough to call this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema already documents all parameters thoroughly. The description restates the metric options and scope intent, but adds little that is not already in the schema. The 'never sum across currencies' caveat is useful but is not a parameter-level semantic addition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a precise verb-object statement: 'Compute a single metric (sum/average/count/max/min) over a filtered set of transactions...' This clearly identifies the tool's action and resource, and differentiates it from sibling tools like get_credits by explicitly stating what it is not. The title and name are generic, but the description fully disambiguates them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit default behavior and clearly routes non-transaction queries such as credits/quota to get_credits instead. However, it does not address sibling aggregation-related tools like group_by, time_series, or top_n, so an agent has less guidance on choosing among those alternatives. Still, the provided context and exclusion are useful and specific.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Bankstatemently toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

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.

Naming Consistency4/5

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.

Tool Count4/5

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.

Completeness4/5

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.

Resources