get_random_articlesDiscover random Wikipedia articles for serendipitous learning. Returns title, introduction text, and page ID.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of random articles to fetch (1-10, default 5) |
| Name | Required | Description | Default |
|---|---|---|---|
| articles | Yes | Array of random article summaries |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "articles": {
+ "description": "Array of random article summaries",
+ "items": {
+ "properties": {
+ "description": {
+ "description": "Short description or null if unavailable",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "extract": {
+ "description": "Article introduction text",
+ "type": "string"
+ },
+ "pageid": {
+ "description": "Wikipedia page ID or null if unavailable",
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "title": {
+ "description": "Article title",
+ "type": "string"
+ }
+ },
+ "required": [
+ "title",
+ "extract",
+ "pageid",
+ "description"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "articles"
+ ],
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "count": 3
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful context about the random behavior and return structure (title, introduction text, page ID), which goes beyond what annotations provide. It does not contradict any annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is exactly two sentences, front-loaded with the primary purpose and followed by the return value. Every word earns its place, with no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one optional parameter, complete annotations, and an output schema, this description is sufficient. It communicates the essential purpose, expected output, and random nature, leaving no critical gaps for the agent to make an informed invocation decision.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'count' has a complete description in the input schema ('Number of random articles to fetch (1-10, default 5)'), so the description need not repeat it. The tool description itself does not elaborate on parameter semantics, but with 100% schema coverage, this is acceptable per the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Discover random Wikipedia articles for serendipitous learning.' The verb 'Discover' combined with 'random' and 'serendipitous' distinguishes it from sibling tools like search_wikipedia or get_article_extract, which target specific articles. It also states the return payload (title, introduction, page ID).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for exploratory discovery ('serendipitous learning') but does not explicitly contrast with alternatives like search_wikipedia or get_article_summary. There is no 'when not to use' guidance or mention of sibling tools, so usage context is only implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The server is named 'wikipedia' but most tools are unrelated Pipeworx/Polymarket tools, so an agent asked to use Wikipedia tools will face a large misleading option set. Even within families there is blurriness: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research overlap, and the five polymarket_* tools have closely related purposes that require reading very long descriptions to disambiguate.
Naming conventions are mixed: some tools use clean verb_noun patterns (search_wikipedia, resolve_entity, validate_claim) while others use product prefixes (ask_pipeworx, pipeworx_trending, polymarket_edges) or noun-phrase names (entity_profile, recent_changes, bet_research). There is no single consistent pattern across the set.
36 tools is already heavy, but it is especially inappropriate for a server named 'wikipedia' — only a handful are actually Wikipedia tools, while the rest belong to unrelated domains (Pipeworx data, Polymarket betting, memory, subscriptions, npm scanning). The count reflects a kitchen-sink scope rather than a focused purpose.
The Wikipedia-reading subset (search, summary, sections, extract, random) is decent but lacks editing, category, or link features. The broader Pipeworx/Polymarket surface is quite comprehensive, so completeness depends entirely on which implicit domain you judge it against; as a 'wikipedia' server it is incomplete, and as a unified data platform the scope is still incoherent.