fynsight: MCP server for DATEV

propose-manual-adjustment

Propose a manual correction booking (Korrekturbuchung) for a month — e.g. an unbooked invoice or an anomaly correction. This does NOT post to the ledger: it creates a PENDING proposal that a human must approve in the web app. Use when the user wants to add a missing cost/revenue on a specific account and cost center.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "account": "<account>",
      "cost_center": "<cost_center>",
      "period": "<period>",
      "amount": "<amount>"
    },
    "name": "propose-manual-adjustment"
  }
}

Input Schema

Name	Required	Description
`note`	No	Optional internal note explaining the correction
`amount`	Yes	Amount in the ledger sign convention: POSITIVE on an expense account books ADDITIONAL expense (an unbooked invoice is positive, never negative), POSITIVE on a revenue account books additional revenue. Use a NEGATIVE amount only to REDUCE a booked amount (e.g. moving cost off an account).
`period`	Yes	Accounting month (YYYY-MM or YYYY-MM-DD)
`account`	Yes	Account as shown in the app: "4321", or with sub-account "8400/130" (account/sub-account, slash). Without a sub-account the sub-account is resolved automatically when the account has exactly one variant; if there are several, the error lists the known variants. Must exist for the tenant.
`cost_center`	Yes	Cost center / Kostenstelle number (e.g. 93)
`description`	No	Booking text, e.g. "Gies Dienstleistung"
`contra_account`	No	Optional contra account (Gegenkonto), same notation: "1200" or "1200/000". Any account the tenant knows: in its chart of accounts or already used as a contra account in its bookings (e.g. bank, personal or balance sheet accounts from a KNW import). A bare number resolves if the tenant knows exactly one variant.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4/5.0

Behavior4/5

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

Beyond the annotations, the description discloses the crucial workflow trait: the call does not post to the ledger but creates a PENDING proposal requiring human approval in the web app. It does not address duplicate handling for the non-idempotent case (whether a repeated call creates a second proposal), which is the main remaining gap.

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?

Three tight sentences, each carrying distinct information: what it creates, that it is not posted, and when to use it. The most important constraint (no ledger posting, human approval) is front-loaded immediately after the purpose.

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 7-parameter mutation tool with full schema documentation and no output schema, the description covers the essential behavioral contract: it is a pending, human-approved proposal rather than a booking. Missing only duplicate/idempotency guidance, which matters given idempotentHint=false.

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 schema already documents every parameter, including sign conventions and account notation. The description only restates that an account and cost center are the target of the correction, adding no syntax or semantics beyond the structured fields.

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

Purpose4/5

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

The description states a specific verb and resource ('Propose a manual correction booking (Korrekturbuchung) for a month') and gives concrete examples (unbooked invoice, anomaly correction). It does not explicitly distinguish itself from the sibling propose-transaction-correction or update-manual-adjustment, so it falls short of full sibling differentiation.

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?

It gives an explicit trigger ('Use when the user wants to add a missing cost/revenue on a specific account and cost center') and implicitly excludes ledger posting by emphasizing the approval workflow. It stops short of naming alternatives such as the transaction-correction or update/withdraw tools for other cases.

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

All fynsight: MCP server for DATEV tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?