Lintelly HR Deutschland

Stellenanzeige: AGG-Check

stellenanzeige_check

Read-onlyIdempotent

Checks a German job ad (Stellenanzeige) for discrimination traps under the AGG (Allgemeines Gleichbehandlungsgesetz), Germany only. Use it before a founder publishes a job ad or after you drafted one: pass the ad text. Returns each risky word with the protected characteristic (Merkmal), the reason and a better wording, plus the parts of a good ad; the text itself is neither stored nor returned.

Input Schema

Name	Required	Description	Default
`anzeigentext`	Yes	Full text of the job ad, at most 3000 characters, without names or contact details

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.

Changed1 schema field changedOct 31, 2026

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 establish read-only, idempotent, non-destructive, closed-world behaviour. The description goes beyond them with a genuine privacy disclosure — the ad text is neither stored nor returned — and previews that results include Merkmal, reason and suggested rewording.

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?

Three sentences, front-loaded with the purpose and scoping constraint, then usage timing, then return/behaviour. A small amount of the return-shape sentence duplicates the output schema, but nothing is padded.

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 single-parameter tool with an output schema, the description covers jurisdiction, timing, data handling and a result preview — enough to call it confidently. Minor residual gap: no note on what happens with non-German or mixed-language text, which the "Germany only" line only partly covers.

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?

With 100% schema coverage on a single parameter, the schema already documents the 3000-character cap and the instruction to omit names and contact details. The description's "pass the ad text" merely restates the schema without adding format or content guidance.

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 verb and resource ("Checks a German job ad") plus the legal frame (AGG) and a hard scope boundary ("Germany only"). It is clearly distinguishable from the nearest sibling, interviewfragen_check, which audits interview questions rather than ad text.

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?

Gives concrete triggering moments: "before a founder publishes a job ad or after you drafted one", and says what to supply. It doesn't name a specific alternative tool to use instead, so it falls just short of full when/when-not routing.

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.