search_jokesSearch Chuck Norris jokes by keyword. Returns matching jokes with text and IDs.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Keyword or phrase to search for within joke text. |
| Name | Required | Description | Default |
|---|---|---|---|
| jokes | Yes | Array of matching jokes | |
| query | Yes | The search query used | |
| total | Yes | Total number of matching jokes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "query": "karate"
+ },
+ {
+ "query": "roundhouse kick"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "jokes": {
+ "description": "Array of matching jokes",
+ "items": {
+ "properties": {
+ "categories": {
+ "description": "List of categories",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "id": {
+ "description": "Unique joke identifier",
+ "type": "string"
+ },
+ "joke": {
+ "description": "The joke text",
+ "type": "string"
+ },
+ "url": {
+ "description": "URL to the joke on chucknorris.io",
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "joke",
+ "categories",
+ "url"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "query": {
+ "description": "The search query used",
+ "type": "string"
+ },
+ "total": {
+ "description": "Total number of matching jokes",
+ "type": "number"
+ }
+ },
+ "required": [
+ "total",
+ "query",
+ "jokes"
+ ],
+ "type": "object"
+}Input schema / examplesRemoved value: -[
- {
- "query": "knock knock"
- },
- {
- "limit": 5,
- "query": "programming"
- }
-]Output 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: +nullOutput 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"
+}Input schema / examplesAdded value: +[
+ {
+ "query": "knock knock"
+ },
+ {
+ "limit": 5,
+ "query": "programming"
+ }
+]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, establishing it as a safe read-only operation. The description adds the behavioral detail that it returns matching jokes with text and IDs, but this is modest and largely intrinsic to a search function.
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 two sentences with no filler. It front-loads the action and directly states the return content.
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?
The tool has a single parameter with full schema coverage, output schema, and comprehensive annotations. The description adequately conveys the tool's purpose and behavior for its simple scope; it doesn't mention pagination or search constraints, but these may be covered by the output schema.
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 input schema has 100% description coverage, with the query parameter clearly defined as 'Keyword or phrase to search for within joke text.' The description's mention of 'keyword' adds no additional meaning beyond the schema.
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 uses a specific verb ('Search') and identifies the resource ('Chuck Norris jokes'), and clarifies the return format ('matching jokes with text and IDs'). This clearly distinguishes it from sibling tools like random_joke or joke_by_category.
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 clearly indicates the tool is for keyword-based search, providing clear context. However, it does not explicitly compare itself to sibling tools or state when not to use it, such as for random jokes or category filtering.
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.
Several tools have overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical query routers, and the five polymarket_* tools all hunt mispricings in subtly different ways. The memory trio (remember/recall/forget) and subscription trio (subscribe/unsubscribe/recent_alerts) are distinct, but the many data-query tools create frequent ambiguity for an agent deciding which one to call.
Naming is a mix of verb_noun (list_categories, resolve_entity, validate_claim), bare nouns (entity_profile, random_joke, deep_research), single verbs (forget, recall), and brand-prefixed nouns (pipeworx_feedback, pipeworx_trending). There's no consistent pattern across the set, so an agent cannot predict a tool's name from its function.
35 tools for a server named 'chucknorris' is an extreme mismatch; only 4 tools actually relate to Chuck Norris jokes. The rest form a sprawling collection of data-research, prediction-market, subscription, and memory utilities that have nothing to do with the stated server identity and overwhelm any agent expecting a simple joke API.
The Chuck Norris joke subset is complete (random, by-category, search, categories), but the overall server attempts many unrelated domains—structured data queries, prediction-market arb, entity profiles, subscriptions, memory—none of which are clearly scoped or fully coherent. The result is a grab-bag with no single domain that feels finished, and the incongruous inclusion of joke tools adds confusion rather than coverage.