Skip to main content
Glama

fynsight: MCP server for DATEV

compute_aggregates

Read-only

Main calculation tool for sums, MoM, YoY, shares. Supports cost_centers, accounts, text_query filters. Use for ALL aggregations. Pages losslessly over groups via after_group/next_cursor; use available_range and never claim 'no data' when it shows data. For yearly/quarterly/overall figures set granularity instead of summing months yourself; totals.sum is the total over all periods in scope regardless of granularity. mom/yoy compare with the previous bucket inside the requested window; for the calendar previous month use get_periodic_summaries with include_previous. With group_by=account every sub-account is its own group: the group key carries account, sub_account (null = none) and account_ref ("8400/130" or "8400"). If the user names a cost center (e.g. "Betriebsrat"), call get_cost_center_list FIRST to resolve its number; never guess the number. scope says what the result covers. scope.pnl_reconciled=true means each month was cross-checked against the P&L; a warning then means bookings are missing — pass it on with period, both amounts and the difference. With text_query, cost_centers or categories the result is a subset by design and is not reconciled against the P&L, so never call it provisional or incomplete for that reason. With text_query, scope.text_match gives matched_sum (the result), unfiltered_sum (all bookings of the same accounts, cost centers and months without the search term) and matched_share_pct: name the result together with unfiltered_sum and the share, e.g. 'X € of Y € on these accounts (Z %)'.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "compute_aggregates"
  }
}

Input Schema

NameRequiredDescriptionDefault
periodsNoYYYY-MM periods. Also accepts the shorthands 'YYYY' and 'YYYY-Qn' (e.g. '2023', '2023-Q2'), which expand to exactly the months the tenant has data for — prefer them over typing out every month, a forgotten month makes a rollup silently too low.
accountsNoAccount numbers
group_byNoGrouping dimensions
categoriesNoAccount categories
operationsNoMetrics to compute (default: ['sum'])
text_queryNoText filter for customer/vendor names
after_groupNoPagination cursor: pass pagination.next_cursor from the previous call to fetch the next page of groups
granularityNoTime bucket of the returned figures: 'month' (default), 'quarter', 'year' or 'total'. Set this whenever the answer needs a figure covering more than one month — never add the monthly values up yourself.
cost_centersNoCost center IDs
share_denominatorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description still adds substantial operational context the annotations cannot: lossless group pagination via after_group/next_cursor, the available_range guard against claiming "no data", and how to interpret scope.pnl_reconciled warnings. However, it never states the return shape for the result rows themselves or any size/rate limits, so it adds real but incomplete behavioral context.

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

Conciseness3/5

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

Purpose is correctly front-loaded and every sentence is substantive, but it is one unbroken paragraph of dense clauses mixing routing rules, pagination, reconciliation caveats and output phrasing guidance. Sectioning or trimming the text_match example would make it markedly easier to scan without losing content.

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?

For a 10-parameter tool with no output schema, the description does heavy lifting: it covers scope.pnl_reconciled semantics, text_match's matched_sum/unfiltered_sum/matched_share_pct, and pagination via next_cursor. It is close to complete, with the result row/list structure only partially implied.

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

Parameters4/5

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

Schema coverage is 90%, so the baseline is 3; the description earns above baseline by explaining cross-parameter semantics the schema cannot, such as why granularity should replace manual month summing and how totals.sum behaves across granularities. It also decodes group_by=account into account, sub_account and account_ref, a structural detail absent from the enum description.

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?

Opens with a specific verb+resource: "Main calculation tool for sums, MoM, YoY, shares," and immediately names the filter dimensions it supports. It is clearly separable from siblings like get_periodic_summaries, get_cost_center_list and get_metric_trend, which are explicitly pointed to.

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?

States the selection rule outright ("Use for ALL aggregations") and names the alternative for the overlapping case ("for the calendar previous month use get_periodic_summaries with include_previous"). It also gives a mandatory prerequisite workflow: resolve cost center numbers via get_cost_center_list FIRST, never guess.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources