Lintelly HR Deutschland

Arbeitszeugnis: Aufbau und Zeugnissprache

arbeitszeugnis

Read-onlyIdempotent

German employment reference (Arbeitszeugnis, Zwischenzeugnis, Endzeugnis), Germany only. Use it when a founder wants a reference written: give the kind of reference and a grade from 1 to 5 per area, never names. Returns the structure with mandatory parts, the coded wording (Zeugnissprache) for each grade, the overall grade with its satisfaction formula, forbidden codes and traps, and the legal claim under § 109 GewO.

Input Schema

Name	Required	Description
`art`	No	endzeugnis (final reference at the end of employment) or zwischenzeugnis (interim reference while employed), default endzeugnis
`ende`	No	Last day of employment, final reference only (YYYY-MM-DD)
`grund`	No	Why the employment ends, final reference only, default ohne (no reason stated)
`beginn`	No	First day of employment (YYYY-MM-DD)
`umfang`	No	qualifiziert (with performance and conduct, the usual case) or einfach (only kind and duration of work), default qualifiziert
`schluss`	No	Closing formula: note (thanks, regret and wishes matching the grade, default), dank (thanks only), keine (none)
`note_fuehrung`	No	Grade for leadership (Führungsleistung), only with fuehrungsverantwortung, 1 (sehr gut) to 5 (mangelhaft), default 2
`note_verhalten`	No	Grade for conduct towards superiors, colleagues and customers (Verhalten), graded separately, 1 (sehr gut) to 5 (mangelhaft), default 2
`note_fachwissen`	No	Grade for expertise (Fachwissen), 1 (sehr gut) to 5 (mangelhaft), default 2
`zwischen_anlass`	No	Occasion of an interim reference, default wunsch (employee asked)
`note_arbeitsweise`	No	Grade for way of working (Arbeitsweise: care, reliability, pace), 1 (sehr gut) to 5 (mangelhaft), default 2
`note_arbeitserfolg`	No	Grade for results (Arbeitserfolg: quality and quantity), 1 (sehr gut) to 5 (mangelhaft), default 2
`fuehrungsverantwortung`	No	The person leads staff (Führungsverantwortung); then note_fuehrung counts toward the overall grade
`note_arbeitsbereitschaft`	No	Grade for willingness to work (Arbeitsbereitschaft: commitment, initiative), 1 (sehr gut) to 5 (mangelhaft), default 2

Output Schema

Name	Required	Description
`stand`	Yes
`fallen`	No
`hinweis`	Yes
`quellen`	Yes
`ergebnis`	Yes	Result of the tool; its fields differ per tool
`rechenweg`	No
`herausgeber`	Yes
`naechster_schritt`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedOct 31, 2026

addedInput schema / properties / beginn / format
```
Added value: +"date"
```
addedInput schema / properties / ende / format
```
Added value: +"date"
```
changedInput schema / properties / note_arbeitsbereitschaft / type
```
Previous value: -"number"New value: +"integer"
```
changedInput schema / properties / note_arbeitserfolg / type
```
Previous value: -"number"New value: +"integer"
```
changedInput schema / properties / note_arbeitsweise / type
```
Previous value: -"number"New value: +"integer"
```
changedInput schema / properties / note_fachwissen / type
```
Previous value: -"number"New value: +"integer"
```
changedInput schema / properties / note_fuehrung / type
```
Previous value: -"number"New value: +"integer"
```
changedInput schema / properties / note_verhalten / type
```
Previous value: -"number"New value: +"integer"
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "ergebnis": {
+      "description": "Result of the tool; its fields differ per tool"
+    },
+    "fallen": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "herausgeber": {
+      "type": "string"
+    },
+    "hinweis": {
+      "type": "string"
+    },
+    "naechster_schritt": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "quellen": {
+      "items": {
+        "properties": {
+          "geprueft_am": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "grund": {
+            "type": "string"
+          },
+          "norm": {
+            "type": "string"
+          },
+          "status": {
+            "enum": [
+              "bestätigt",
+              "noch nicht bestätigt",
+              "Prüfung überfällig"
+            ],
+            "type": "string"
+          },
+          "url": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "norm"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "rechenweg": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "stand": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "ergebnis",
+    "quellen",
+    "hinweis",
+    "stand",
+    "herausgeber"
+  ],
+  "type": "object"
+}

First observedOct 23, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world behavior, so the description's job is to add meaning, which it does: it discloses the returned content (mandatory parts, coded Zeugnissprache per grade, overall grade with satisfaction formula, forbidden codes and traps) and the legal basis (§ 109 GewO). It leaves open formatting/length of the output, but the safety profile and scope are fully consistent with the annotations.

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?

Two sentences, front-loaded with the resource and jurisdiction, followed by when-to-use and return contents; nothing is redundant with the title. The enumeration of returned elements is slightly long relative to the presence of an output schema, but it reads as scope-setting rather than padding.

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 14-parameter, zero-required generator with an output schema and rich annotations, the description covers what it does, when to use it, an input constraint (no names), and the substantive scope of the result including the legal claim. Minor gaps remain (e.g., defaults being optional so no required input is needed, output language/format), but nothing that would cause a wrong invocation.

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% with 14 well-documented, mostly enum-or-range parameters, so the schema carries the parameter burden. The description adds two useful framing points not in the schema itself – that grades are per area on a 1–5 scale and that names must never be supplied – but does not explain the interaction between art/ende/grund/zwischen_anlass beyond what the schema already states.

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?

States a specific artifact (German employment reference, including Zwischenzeugnis/Endzeugnis) plus a jurisdiction constraint ('Germany only'), and the second sentence makes the action concrete: drafting a reference from kind and per-area grades. No sibling tool in the list covers Arbeitszeugnis, so it is unambiguously distinguishable from the Abmahnung/Kündigung/Vertrag families.

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?

'Use it when a founder wants a reference written' gives a clear triggering condition, and 'give the kind of reference and a grade from 1 to 5 per area, never names' constrains the intended inputs. It does not name an alternative tool or an explicit case where not to use it, which keeps it below a 5.

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

All Lintelly HR Deutschland 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.