fynsight: MCP server for DATEV

draft-report-comment

Create an AI DRAFT explanation (status ai_draft) for a position of the month report. The draft has a short form (summary: one sentence saying why the number deviates, no figures) and an optional detail (may name single amounts from the material). The material is the position's figures plus the notes and clarification answers of the decided cases of the run that belong to it. Drafts are only created on request (here or by a click in the app), never automatically: check list-comment-status first and draft only for positions that are still open. It is NEVER published automatically — the user reviews and publishes it in the app. The response returns summary and detail. Existing explanations are never overwritten silently (see replace_published).

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": {
      "run_id": "<run_id>",
      "target_type": "<target_type>",
      "target_key": "<target_key>"
    },
    "name": "draft-report-comment"
  }
}

Input Schema

Name	Required	Description
`run_id`	Yes	UUID of the run
`target_key`	Yes	Position key: P&L label (tenant category), metric key (e.g. "ebitda"), cost center number, or "total".
`target_type`	Yes	Position type
`instructions`	No	Optional hints for the draft
`replace_published`	No	Required true to replace a comment that is already published (approved in the app); without it the call is rejected with COMMENT_PUBLISHED and the published text stays.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds context the annotations cannot: drafts are never auto-published, a human reviews and publishes in the app, and existing explanations are not silently overwritten (a published comment needs replace_published or the call fails with COMMENT_PUBLISHED). It also defines what the material is (figures plus notes and clarification answers of the run's decided cases).

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

Conciseness4/5

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

The description is information-dense and front-loaded, with the key constraint (draft, never published) stated before the operational detail. Its only weakness is slight redundancy, since the no-automatic-creation point and the never-published point are each restated, and the second gains little from the repetition.

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?

There is no output schema, but the description says the response returns summary and detail, so the missing schema is covered. With five parameters all documented in the schema and the behavioral boundaries of the draft workflow spelled out, an agent has everything it needs to invoke the tool correctly.

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 100%, so the baseline is 3. The description earns a point by explaining what run_id and target identify in substance: the position's figures plus the notes and clarification answers of the decided cases of that run. The instructions parameter is still only explained by its schema, and replace_published is cross-referenced rather than unpacked.

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 first sentence names a specific verb and resource: create an AI draft explanation with status ai_draft for a position of the month report. It immediately distinguishes the artifact from a published comment, and the naming of the two output fields (summary, detail) makes the tool's product tangible.

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?

It gives an explicit precondition: check list-comment-status first, and draft only for positions that are still open. It also states that drafts are never created automatically, only here or via an app click, and it routes the overwrite case to replace_published. That is when-to-use plus a named sibling alternative.

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?