fynsight: MCP server for DATEV

update-manual-adjustment

DestructiveIdempotent

Edit a PENDING manual correction proposal (amount, account, cost center, description, note, period). Approved bookings cannot be edited — delete them in the app instead.

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": {
      "id": "<id>"
    },
    "name": "update-manual-adjustment"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	UUID of the pending proposal
`note`	No	New note
`amount`	No	New amount, in the ledger sign convention: POSITIVE on an expense account books additional expense, POSITIVE on a revenue account books additional revenue. Use a NEGATIVE amount only to REDUCE a booked amount.
`period`	No	New month (YYYY-MM or YYYY-MM-DD)
`account`	No	New account, "4321" or "8400/130". Without a sub-account it is resolved automatically when the account has exactly one variant; otherwise pass the full account/sub-account.
`cost_center`	No	New cost center
`description`	No	New booking text
`contra_account`	No	New contra account, same notation. 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).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuine context beyond that by gating the operation on PENDING state. However, it says nothing about partial-update semantics — whether fields omitted from the call are preserved or cleared — which is the key risk for a destructive edit.

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?

Two sentences, front-loaded with the state constraint before the exclusion, and no filler. Every clause conveys actionable information.

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 8 parameters fully documented in the schema and annotations present, the description supplies the missing state gate and the negative case. It is nearly complete, but leaves open whether unspecified fields are left untouched and what the call returns (no output schema exists).

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%, including detailed sign-convention and account-notation notes, so the schema carries the parameter burden. The description only restates the editable field names, adding no meaning beyond what the schema already documents; baseline 3 applies.

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?

"Edit a PENDING manual correction proposal" gives a specific verb, a specific resource, and a state qualifier that separates it cleanly from propose-manual-adjustment (create) and withdraw-manual-adjustment (remove). The parenthetical field list further pins down the scope of the edit.

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 states a hard precondition (only PENDING proposals are editable) and an explicit exclusion (approved bookings cannot be edited), which is exactly the routing information an agent needs. It does not name the sibling tools an agent should use instead for other cases, and "delete them in the app instead" is vague given a withdraw-manual-adjustment tool exists.

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?