Skip to main content
Glama
ohneben

Buchhaltungsbutler MCP

by ohneben
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Reports: get sums report

reports_get_sums
Read-onlyIdempotent

Fetches a completed sums and balances report from the accounting system. Use this after the report has finished generating to retrieve the final data.

Instructions

🟢 READ-ONLY: Fetches data. Makes no changes to the accounting records.

get sums report

Returns a previously created sums report ("Summen- und Saldenliste").

Reports are generated asynchronously, so a report is only available once its generation has been finished. Note that creating a new report of the same type replaces the previously created one.

Use to read a sums and balances report that reports_create_sums has finished generating. Step two of two.

For the individual bookings behind one posting account, use reports_get_sums_ledger.

Endpoint: POST /reports/get/sums

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
get_filesNoIf true, the report's files will be included as base64 encoded strings. If specified, the field will be validated.
report_id_by_customerYesThe id_by_customer of the report, as returned when the report was created

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
filesNoOnly contained if get_files has been specified. Provides the keys 'csv', 'pdf' and 'csv_archive', each holding the base64 encoded content of the report's file, or null if the file is not available – because it has not been requested when the report was created, because it is still being created or because it is not available anymore.
reportNoThe report's data, containing the keys 'integrityError', 'countPostingsWithDateVatEffectiveNotConsideredInReport' and 'sums'. The sums are keyed by postingaccount number, and every entry provides the 'postingaccount' itself as well as the unformatted values 'balanceBeforeDebit', 'balanceBeforeCredit', 'balanceBeforeAbsolute', 'balanceBeforeSide', 'sumPeriodDebit', 'sumPeriodCredit', 'balanceAfterDebit', 'balanceAfterCredit', 'balanceAfterAbsolute' and 'balanceAfterSide'.
messageNoblank
successYesSuccess boolean

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.2
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "files": {
+      "description": "Only contained if get_files has been specified. Provides the keys 'csv', 'pdf' and 'csv_archive', each holding the base64 encoded content of the report's file, or null if the file is not available – because it has not been requested when the report was created, because it is still being created or because it is not available anymore.",
+      "type": "object"
+    },
+    "message": {
+      "description": "blank",
+      "type": "string"
+    },
+    "report": {
+      "description": "The report's data, containing the keys 'integrityError', 'countPostingsWithDateVatEffectiveNotConsideredInReport' and 'sums'.\n\nThe sums are keyed by postingaccount number, and every entry provides the 'postingaccount' itself as well as the unformatted values 'balanceBeforeDebit', 'balanceBeforeCredit', 'balanceBeforeAbsolute', 'balanceBeforeSide', 'sumPeriodDebit', 'sumPeriodCredit', 'balanceAfterDebit', 'balanceAfterCredit', 'balanceAfterAbsolute' and 'balanceAfterSide'.",
+      "type": "object"
+    },
+    "success": {
+      "description": "Success boolean",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "success"
+  ],
+  "type": "object"
+}
  2. Changed1 schema field changedv1.1.0
    • removedInput schema / properties / api_key
      Removed value: -{
-  "description": "Optional. The BB customer api_key to act on. Defaults to the BB_API_KEY configured on the server — only set this to target a different customer.",
-  "type": "string"
-}
  3. Addedv1.0.2

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: reports are generated asynchronously, a report is only available after generation finishes, and creating a new report of the same type replaces the previous one. This explains statefulness and availability semantics that annotations cannot 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 well-structured and front-loaded: the READ-ONLY warning and one-line summary come first, followed by the async caveat, usage instruction, sibling alternative, and endpoint. Every sentence earns its place, and the emoji/uppercase warning is immediately visible.

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

Completeness5/5

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

For a read-only retrieval tool with a rich output schema, full parameter documentation, and annotations covering safety, the description is complete. It explains the async generation constraint, the replacement behavior, the two-step workflow, and the sibling alternative. An agent has everything needed to call it 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 description coverage is 100%, so the schema already documents both parameters. The description adds context by explaining that `report_id_by_customer` is the id returned when the report was created, which reinforces the two-step workflow, but it does not add new parameter-level detail beyond the schema. Baseline 3 is appropriate.

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 states a specific verb ('Returns'), a specific resource ('previously created sums report'), and explicitly distinguishes it from the sibling `reports_get_sums_ledger`. It also names the companion creation tool `reports_create_sums`, making the tool's role in a two-step workflow unmistakable.

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

Usage Guidelines5/5

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

The description explicitly says to use this tool to read a sums report that `reports_create_sums` has finished generating, and calls it 'step two of two.' It also gives an exclusion: for individual bookings behind one posting account, use `reports_get_sums_ledger`. This is clear when-to-use and when-not-to-use guidance.

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

Deploy Server

Other Tools