jokes

Search Jokes

search_jokes

Read-onlyIdempotent

Search jokes by keyword or phrase. Returns matching jokes with categories, types, and content flags.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	Keyword or phrase to search for within joke text.
`amount`	No	Number of jokes to return. Defaults to 5.
`category`	No	Limit search to a category. One of: Any, Programming, Misc, Dark, Pun, Spooky, Christmas. Defaults to "Any".
`safe_mode`	No	When true (the default), only return jokes JokeAPI flags as safe. Set false to include Dark and other unsafe-flagged categories.

Output Schema

TableJSON Schema

Name	Required	Description
`jokes`	Yes	Array of matching jokes
`query`	Yes	Search query used
`total`	Yes	Total number of matching jokes
`category`	Yes	Category searched

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedAug 3, 2026

addedInput schema / properties / safe_mode

Added value: +{
+  "description": "When true (the default), only return jokes JokeAPI flags as safe. Set false to include Dark and other unsafe-flagged categories.",
+  "type": "boolean"
+}

Changed2 schema fields changedMay 24, 2026

addedInput schema / examples

Added value: +[
+  {
+    "amount": 10,
+    "category": "Programming",
+    "query": "programmer"
+  },
+  {
+    "amount": 5,
+    "query": "Christmas"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "category": {
+      "description": "Category searched",
+      "type": "string"
+    },
+    "jokes": {
+      "description": "Array of matching jokes",
+      "items": {
+        "properties": {
+          "category": {
+            "description": "Joke category",
+            "type": "string"
+          },
+          "delivery": {
+            "description": "Punchline for two-part jokes",
+            "type": "string"
+          },
+          "joke": {
+            "description": "Full joke text for single-part jokes",
+            "type": "string"
+          },
+          "safe": {
+            "description": "Whether joke is flagged as safe",
+            "type": "boolean"
+          },
+          "setup": {
+            "description": "Setup text for two-part jokes",
+            "type": "string"
+          },
+          "type": {
+            "description": "Joke type",
+            "enum": [
+              "single",
+              "twopart"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "category",
+          "safe"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "query": {
+      "description": "Search query used",
+      "type": "string"
+    },
+    "total": {
+      "description": "Total number of matching jokes",
+      "type": "number"
+    }
+  },
+  "required": [
+    "total",
+    "query",
+    "category",
+    "jokes"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedMay 13, 2026

removedInput schema / examples

Removed value: -[
-  {
-    "query": "knock knock"
-  },
-  {
-    "limit": 5,
-    "query": "programming"
-  }
-]

changedOutput schema / (root)

Previous value: -{
-  "properties": {
-    "jokes": {
-      "description": "Array of matching jokes",
-      "items": {
-        "properties": {
-          "id": {
-            "description": "Unique identifier for the joke",
-            "type": "string"
-          },
-          "joke": {
-            "description": "The joke text",
-            "type": "string"
-          }
-        },
-        "required": [
-          "id",
-          "joke"
-        ],
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "query": {
-      "description": "The search term used",
-      "type": "string"
-    },
-    "total": {
-      "description": "Total number of jokes matching the query",
-      "type": "number"
-    }
-  },
-  "required": [
-    "total",
-    "query",
-    "jokes"
-  ],
-  "type": "object"
-}New value: +null

Changed1 schema field changedMay 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "jokes": {
+      "description": "Array of matching jokes",
+      "items": {
+        "properties": {
+          "id": {
+            "description": "Unique identifier for the joke",
+            "type": "string"
+          },
+          "joke": {
+            "description": "The joke text",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "joke"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "query": {
+      "description": "The search term used",
+      "type": "string"
+    },
+    "total": {
+      "description": "Total number of jokes matching the query",
+      "type": "number"
+    }
+  },
+  "required": [
+    "total",
+    "query",
+    "jokes"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "query": "knock knock"
+  },
+  {
+    "limit": 5,
+    "query": "programming"
+  }
+]

First observedApr 14, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, fully covering the safety profile. The description adds the search semantics (keyword-based matching) and that results include categories/types/content flags. It doesn't describe pagination, result limits behavior, or error conditions, but with strong annotation coverage, a 3 is appropriate since the description adds modest extra context.

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?

The description is a single efficient sentence that states the action and the output content. It's front-loaded with the core purpose. It's slightly terse—could mention safe_mode behavior explicitly in the description—but it is compact and free of filler.

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?

With a strong annotation set (readOnly, openWorld, idempotent) and a rich output schema plus 100% parameter coverage, the description is largely adequate. For a search tool, it reasonably conveys the core purpose and output. It could mention result limits or empty-result behavior, but given the abundant annotation and schema support, this is complete enough.

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% per the context signal, with all four parameters (query, amount, category, safe_mode) having descriptions in the schema. The description itself adds minimal parameter-level detail—it mentions categories and content flags generically but 'content flags' loosely maps to safe_mode. Since the schema handles the heavy lifting, a baseline 3 is correct.

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 clearly states it searches jokes by keyword or phrase and what returns (matching jokes with categories, types, and content flags). The verb+resource ('Search jokes') is specific and distinguishes it from sibling tools like get_joke (which likely returns a single joke) and get_joke_categories (which lists categories).

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?

The description conveys clear context for when to use—when searching jokes by keyword. It distinguishes implicitly from get_joke (single joke retrieval) through the search semantics. However, it doesn't explicitly state when NOT to use it or name an alternative tool, though given the large sibling list it differentiates well by function.

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

All jokes tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.3/5.0

Disambiguation1/5

The server contains 4 joke-related tools and 31 tools from the Pipeworx data ecosystem, which are entirely unrelated. An agent cannot easily distinguish whether to use a joke tool or a data tool, causing extreme ambiguity.

Naming Consistency2/5

Tool names within the joke subset (e.g., get_joke, search_jokes) and Pipeworx subset (e.g., ask_pipeworx, entity_profile) are individually consistent, but the overall set has no unified naming pattern or domain signal, making the server's purpose unclear.

Tool Count1/5

With 35 tools, the count is excessive for a jokes-themed server. Only 4 tools are joke-related; the remaining 31 belong to a completely different domain, making the tool count highly inappropriate.

Completeness1/5

The joke coverage (get, search, categories, flags) is minimal but functional. However, the server as a whole is a Frankenstein of unrelated domains, lacking a coherent surface. The overwhelming majority of tools are irrelevant to the server name.

Search Jokes

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources