Wikipedia

Search Wikipedia

search_wikipedia

Read-onlyIdempotent

Search Wikipedia for encyclopedic facts, sports event schedules, medal tables, officeholder rosters and biographies. Covers multi-sport games and tournaments edition by edition — Olympics, Asian Games, Commonwealth Games, Pan American Games, SEA Games, World Cup — with per-sport competition schedules, session dates, venues, results and medal tables, each on its own article ("Table tennis at the 2026 Asian Games", "Athletics at the 2028 Summer Olympics"). Use it when the article title is NOT predictable from the question, to find the exact title, then read the article body with get_article_extract; when the title IS predictable ("Table tennis at the 2026 Asian Games") skip straight to get_article_extract, since a search snippet is one truncated line. Also the right tool for government composition and officeholder rosters — "current cabinet members of Japan", "list of ministers and their positions", "who is in the German government", "cabinet of 2025" — Wikipedia keeps cabinet, ministry, and government lists current for every country. And for general knowledge: "who is X", "what is Y", "history of Z", definitions. Returns matching article titles, snippets, page IDs, word counts. Chain with get_article_extract for the full text or a single section. Cheaper + more structured than scraping web search results; covers ~7M English articles updated continuously by the Wikipedia community.

Input Schema

Name	Required	Description	Default
`limit`	No	Number of results to return (1-50, default 10)
`query`	Yes	Search query, in ENGLISH — this searches the English Wikipedia, and a query in another language returns 0 hits. Translate non-English questions into English keywords first ("日本现任内阁成员名单" → "current Japan cabinet members").

Output Schema

Name	Required	Description	Default
`results`	Yes	Array of search result objects
`total_hits`	Yes	Total number of matching articles

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 23, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "query": "artificial intelligence"
-  },
-  {
-    "limit": 5,
-    "query": "climate change"
-  }
-]New value: +[
+  {
+    "query": "artificial intelligence"
+  },
+  {
+    "limit": 5,
+    "query": "climate change"
+  },
+  {
+    "limit": 5,
+    "query": "2026 Asian Games table tennis"
+  }
+]

Changed1 schema field changedAug 12, 2026

changedInput schema / properties / query / description

Previous value: -"Search query"New value: +"Search query, in ENGLISH — this searches the English Wikipedia, and a query in another language returns 0 hits. Translate non-English questions into English keywords first (\"日本现任内阁成员名单\" → \"current Japan cabinet members\")."

Changed1 schema field changedMay 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "results": {
+      "description": "Array of search result objects",
+      "items": {
+        "properties": {
+          "pageid": {
+            "description": "Wikipedia page ID",
+            "type": "number"
+          },
+          "snippet": {
+            "description": "HTML-stripped preview text",
+            "type": "string"
+          },
+          "title": {
+            "description": "Article title",
+            "type": "string"
+          },
+          "wordcount": {
+            "description": "Word count of article",
+            "type": "number"
+          }
+        },
+        "required": [
+          "title",
+          "snippet",
+          "pageid",
+          "wordcount"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total_hits": {
+      "description": "Total number of matching articles",
+      "type": "number"
+    }
+  },
+  "required": [
+    "total_hits",
+    "results"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "query": "artificial intelligence"
+  },
+  {
+    "limit": 5,
+    "query": "climate change"
+  }
+]

First observedApr 14, 2026

TDQS

A4.5/5.0

Behavior4/5

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

The annotations already declare the tool read-only, non-destructive, idempotent, and open-world. The description adds value beyond those annotations: it discloses that results are a single truncated line, that the search covers ~7M continuously updated English Wikipedia articles, and that direct chaining with get_article_extract is required for full content. This is a meaningful behavioral disclosure without contradicting the annotation set.

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?

It is a long description but every sentence adds useful context: exact examples, routing conditions, types of search results returned, chaining behavior, and a comparison to web scraping. The main purpose is front-loaded, and even the longer portions use concrete examples ('Table tennis at the 2026 Asian Games', 'current cabinet members of Japan'). No wasted sentences.

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?

The description explains what is returned, when to use the tool, how to combine it with get_article_extract, and even mentions the scale and update cadence of the corpus. The output schema is already present, so the description needn't enumerate every return field. For the complexity of the tool and the sibling set, this is as complete as one can expect.

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 coverage is 100%: the input schema already describes both 'query' and 'limit', including ranges and a well-known English-language restriction. The description adds no new parameter-specific detail aside from implying the query is for Wikipedia search. At 100% schema coverage, the baseline of 3 is appropriate.

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 description states a clear verb and resource pair ('Search Wikipedia for encyclopedic facts') and enumerates a broad but specific set of use cases (sports schedules, medals, cabinet rosters, biographies). It also differentiates itself from get_article_extract by explicitly saying when the article title is predictable, you should skip directly to get_article_extract.

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?

The description gives highly explicit routing: use this tool 'when the article title is NOT predictable', and when the title IS predictable, 'skip straight to get_article_extract'. It also names a dedicated domain (government composition and officeholder rosters) and mentions it should be chained with get_article_extract for full content. No ambiguity about which tool to pick.

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

All Wikipedia 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.