recipesFetch a paginated list of fake recipes from DummyJSON. Supports limit, skip, and field selection via select. Returns name, ingredients, instructions, prep time, and cuisine.
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| limit | No | ||
| select | No |
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | Number of recipes skipped | |
| limit | No | Limit of recipes returned | |
| total | No | Total recipe count | |
| recipes | No | List of recipes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "limit": 10,
+ "skip": 0
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "limit": {
+ "description": "Limit of recipes returned",
+ "type": "number"
+ },
+ "recipes": {
+ "description": "List of recipes",
+ "items": {
+ "properties": {
+ "caloriesPerServing": {
+ "description": "Calories per serving",
+ "type": "number"
+ },
+ "cookTimeMinutes": {
+ "description": "Cook time in minutes",
+ "type": "number"
+ },
+ "cuisine": {
+ "description": "Cuisine type",
+ "type": "string"
+ },
+ "difficulty": {
+ "description": "Difficulty level",
+ "type": "string"
+ },
+ "id": {
+ "description": "Recipe ID",
+ "type": "number"
+ },
+ "image": {
+ "description": "Recipe image URL",
+ "type": "string"
+ },
+ "ingredients": {
+ "description": "List of ingredients",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "instructions": {
+ "description": "Cooking instructions",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "name": {
+ "description": "Recipe name",
+ "type": "string"
+ },
+ "prepTimeMinutes": {
+ "description": "Prep time in minutes",
+ "type": "number"
+ },
+ "rating": {
+ "description": "Recipe rating",
+ "type": "number"
+ },
+ "reviewCount": {
+ "description": "Number of reviews",
+ "type": "number"
+ },
+ "servings": {
+ "description": "Number of servings",
+ "type": "number"
+ },
+ "tags": {
+ "description": "Recipe tags",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "userId": {
+ "description": "User ID of recipe author",
+ "type": "number"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "skip": {
+ "description": "Number of recipes skipped",
+ "type": "number"
+ },
+ "total": {
+ "description": "Total recipe count",
+ "type": "number"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, covering safety and idempotency. The description adds minimal context by listing return fields (name, ingredients, etc.) but does not disclose additional behavioral traits beyond 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 two sentences with no fluff, front-loading the main purpose and key features. Every sentence contributes meaning.
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?
With an output schema present, the description does not need to detail return values, but it mentions key fields. It covers pagination and field selection. However, it lacks details on default pagination behavior or ordering, which would be helpful for a complete understanding.
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?
Schema description coverage is 0%, and the description only names the three parameters (limit, skip, select) without explaining their meanings, constraints, or defaults. While parameter names are somewhat self-explanatory, the description fails to add significant value beyond the schema's property names.
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 fetches a paginated list of fake recipes from DummyJSON, specifying the resource and source. It distinguishes from sibling 'recipe' (singular) which likely retrieves a single recipe.
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 usage through list operations with pagination and field selection, but does not explicitly state when to use this tool versus alternatives like 'recipe'. It provides no exclusion criteria or when-not-to-use guidance.
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.
Many tools have overlapping purposes, e.g., multiple tools for data retrieval (ask_pipeworx, ask_pipeworx_grounded, deep_research, entity_profile) that differ only in nuance, and the inclusion of both DummyJSON and Pipeworx tools creates confusion about which domain to use for what. Agents will struggle to select the correct tool.
Naming conventions are mixed: Pipeworx tools use diverse patterns (verb_noun like 'validate_claim', noun like 'entity_profile', verb like 'forget'), while DummyJSON tools use simple nouns (posts, comments). No consistent pattern across the set.
43 tools is excessive for a server named 'Dummyjson'. The majority are Pipeworx tools unrelated to fake data, making the set feel bloated and unfocused. The count is too large for the apparent scope.
For a fake data API, the set is incomplete: it only provides read operations (fetch, search) with no create, update, or delete capabilities. However, for the Pipeworx portion, the read coverage is extensive, so it's not severely lacking overall.