raumnebenan

Search articles

search_articles

Read-onlyIdempotent

Performs case-insensitive full-text search across published articles. Returns matching articles with summary metadata, category, tags, and URLs (no body markdown). Use it when the user asks about a specific topic or method (e.g. "kano model", "customer journey"). Then call get_article_details_by_slugs with the returned article_slug values to read full content. Optional page/per return a slice and next_page while more remain; without them the complete list is returned.

Input Schema

Name	Required	Description
`per`	No	Optional items per page (default 20 when page is set, max 100).
`page`	No	Optional 1-based page. Omit both page and per to receive the complete list.
`query`	Yes	The search query string

Output Schema

Name	Required	Description	Default
`data`	Yes
`source`	Yes
`retrieved_at`	Yes
`copyright_holder`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 17, 2026

addedInput schema / properties / page

Added value: +{
+  "description": "Optional 1-based page. Omit both page and per to receive the complete list.",
+  "maximum": 10000,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / per

Added value: +{
+  "description": "Optional items per page (default 20 when page is set, max 100).",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}

addedOutput schema / properties / data / properties / next_page

Added value: +{
+  "description": "The next page number; absent on the last page.",
+  "minimum": 2,
+  "type": "integer"
+}

addedOutput schema / properties / data / properties / page

Added value: +{
+  "description": "The returned page (1-based).",
+  "minimum": 1,
+  "type": "integer"
+}

addedOutput schema / properties / data / properties / per

Added value: +{
+  "description": "Items per page.",
+  "minimum": 1,
+  "type": "integer"
+}

Changed2 schema fields changedOct 16, 2026

addedInput schema / properties / query / minLength
```
Added value: +1
```

changedOutput schema / properties / data / properties / hint / description

Previous value: -"Guidance for the agent when no articles were found."New value: +"Guidance for the agent when no articles were found or some requested identifiers could not be resolved."

Changed7 schema fields changedOct 16, 2026

addedInput schema / properties / query / maxLength
```
Added value: +200
```

removedOutput schema / properties / articles

Removed value: -{
-  "items": {
-    "properties": {
-      "article_slug": {
-        "type": "string"
-      },
-      "article_uuid": {
-        "type": "string"
-      },
-      "author": {
-        "type": "string"
-      },
-      "category": {
-        "type": "string"
-      },
-      "copyright_holder": {
-        "type": "string"
-      },
-      "is_part_of_story": {
-        "type": "string"
-      },
-      "last_article_update": {
-        "type": "string"
-      },
-      "original_publishing_date": {
-        "type": "string"
-      },
-      "related_articles_by_friendly_url": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "source_url": {
-        "type": "string"
-      },
-      "summary": {
-        "type": "string"
-      },
-      "tags": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "title": {
-        "type": "string"
-      }
-    },
-    "required": [],
-    "type": "object"
-  },
-  "type": "array"
-}

addedOutput schema / properties / copyright_holder
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / data

Added value: +{
+  "properties": {
+    "articles": {
+      "description": "The list of articles.",
+      "items": {
+        "properties": {
+          "article_slug": {
+            "type": "string"
+          },
+          "article_uuid": {
+            "format": "uuid",
+            "type": "string"
+          },
+          "author": {
+            "type": "string"
+          },
+          "body_markdown": {
+            "type": "string"
+          },
+          "category": {
+            "type": "string"
+          },
+          "copyright_holder": {
+            "type": "string"
+          },
+          "is_part_of_story": {
+            "type": "string"
+          },
+          "last_article_update": {
+            "format": "date-time",
+            "type": "string"
+          },
+          "original_publishing_date": {
+            "format": "date-time",
+            "type": "string"
+          },
+          "related_articles_by_friendly_url": {
+            "description": "Slugs of related articles.",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "source_url": {
+            "format": "uri",
+            "type": "string"
+          },
+          "summary": {
+            "type": "string"
+          },
+          "tags": {
+            "description": "Tags for the article.",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "title": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "source_url",
+          "copyright_holder",
+          "original_publishing_date",
+          "last_article_update",
+          "title",
+          "summary",
+          "article_slug",
+          "related_articles_by_friendly_url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "hint": {
+      "description": "Guidance for the agent when no articles were found.",
+      "type": "string"
+    },
+    "invalid": {
+      "description": "List of requested identifiers that were invalid.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "not_found": {
+      "description": "List of requested identifiers that were not found.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "total": {
+      "description": "The total number of articles.",
+      "minimum": 0,
+      "type": "integer"
+    },
+    "unavailable": {
+      "description": "List of requested identifiers that could not be fetched due to upstream issues.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "total",
+    "articles"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / retrieved_at

Added value: +{
+  "format": "date-time",
+  "type": "string"
+}

addedOutput schema / properties / source
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / required

Previous value: -[]New value: +[
+  "source",
+  "copyright_holder",
+  "retrieved_at",
+  "data"
+]

First observedJun 2, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive safety, so the bar is lower, but the description adds real behavior: matches are case-insensitive, results carry summary metadata/category/tags/URLs and explicitly NOT body markdown. It also discloses pagination semantics (next_page while more remain; complete list when page/per omitted). Minor gap: no note on match ranking or empty-result behavior.

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?

Dense, front-loaded paragraph that goes purpose -> output shape -> when to use -> next step -> pagination in that order, with no filler sentences. Every clause carries actionable information.

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?

For a 3-param search tool with annotations covering the safety profile and an output schema covering return values, the description supplies the missing pieces: search breadth, result contents, pagination contract, and the follow-up tool. Nothing an agent needs to invoke it correctly is absent.

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 baseline is 3, but the description adds semantics the schema does not carry: the returned next_page field and the contrast between sliced and complete-list modes. It largely restates the schema's page/per default behavior rather than adding new syntax detail, keeping it just above baseline.

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+resource (case-insensitive full-text search over published articles) and constrains it to published articles, which separates it from list_articles and get_articles_by_tag. The agent knows exactly what this tool does without opening the schema.

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?

Explicitly says when to use it ('when the user asks about a specific topic or method', with concrete examples) and prescribes the follow-up call to get_article_details_by_slugs for full content. This is a clear when-to-use plus a named next step, leaving nothing to inference.

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

All raumnebenan 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?