Canadian grocery flyer deals and recipes by item, store, postal code, cuisine, or diet. No auth.
Scored across 3 tools
get_flyer_deals operates on grocery flyer deals, while search_meals and get_recipe both operate on recipes. The recipe tools are clearly divided into discovery versus detail retrieval, leaving no overlapping or ambiguous boundaries.
The names follow a clear get_/search_ verb prefix with descriptive noun objects, making them predictable. The only minor inconsistency is mixing search_ and get_ for related recipe operations, but the meaning is still obvious.
Three tools is on the lower end, but each tool earns its place by covering a distinct high-level user need: finding deals, searching recipes, and viewing recipe details. The count feels compact rather than insufficient for a consumer-focused server.
The core workflows are covered: discovering current grocery deals and searching/retrieving recipes. There are no severe dead ends, though the set could benefit from conveniences like a store list or recipe-to-ingredient deal matching.
Search current Canadian grocery flyer deals by item name or store.
Covers FreshCo, Costco, Walmart, Food Basics, and more. All returned deals are currently valid and from the latest successful flyer fetch per store.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results | |
| query | No | Item name to search deals for (e.g. paneer, milk, rice) | |
| store | No | Filter by store name (e.g. FreshCo, Costco) | |
| postal_code | No | Canadian postal code for location-aware deals (e.g. L4B1C3) |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as readOnly and non-destructive. The description adds valuable behavior beyond that: returned deals are guaranteed to be currently valid and are sourced from the latest successful flyer fetch per store. This sets expectations about result freshness and coverage.
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 compact and front-loaded with the core search action, then adds store coverage and freshness guarantees. Every sentence contributes practical information with no filler or repetition of the title.
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 description, combined with the exhaustive input schema and available readOnly annotations, supports correct invocation well. It lacks explicit guidance on result ordering or empty-query behavior, but the output schema and the stated valid-date guarantee cover most agent needs.
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 coverage is 100%, so every parameter already has descriptions and examples. The tool description reinforces the query and store concepts but does not add significant new meaning beyond the schema. Baseline 3 is appropriate.
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 states a specific verb, resource, and scope: 'Search current Canadian grocery flyer deals by item name or store.' This clearly distinguishes it from sibling tools like get_recipe and search_meals, since they target recipes/meals rather than flyer deals.
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 communicates a clear usage context: use this for current Canadian grocery flyer deals, searchable by item, store, and postal code. It does not explicitly name alternatives or state when not to use it, but the subject matter is clearly different from the siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get full recipe details for a specific meal, including scaled ingredients and steps.
| Name | Required | Description | Default |
|---|---|---|---|
| meal_id | Yes | Meal ID from search_meals (UUID) |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is well covered. The description adds a useful statement about returning scaled ingredients and steps, which clarifies what the operation yields. No contradiction exists between description and 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 one focused sentence that says exactly what the tool does and what it returns. It is front-loaded with the main purpose and includes no filler or repetition. Every part earns its place.
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?
This is a simple, single-parameter read-only tool with a rich output schema, so the description does not need much more. The parameter is fully documented in the schema and the purpose/return content is clearly stated. The agent has enough context to select and invoke this tool correctly.
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 100% and the meal_id parameter is already documented well as 'Meal ID from search_meals (UUID).' The description references the meal concept but adds no significant parameter details beyond the schema. Baseline 3 is appropriate because the schema carries the semantic weight.
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 states a specific verb and resource: 'Get full recipe details for a specific meal.' It also specifies the content that distinguishes this from other tools — 'scaled ingredients and steps.' This clearly separates it from search_meals and get_flyer_deals.
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 this is for fetching details for one specific meal rather than searching or browsing. The input schema reinforces the intended flow by requiring a meal_id from search_meals. It could be stronger with an explicit when-not-to-use statement, but the usage context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search NoshUp's recipe catalogue by cuisine, dietary preference, ingredient, or meal type.
The query matches both meal names and recipe ingredients.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results | |
| query | No | Dish name, cuisine type, or ingredient to search for | |
| cuisine | No | Filter by cuisine | |
| dietary | No | Dietary constraints (vegetarian, vegan, gluten_free, nut_allergy) | |
| meal_type | No | Filter by meal type |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral detail that the query matches both meal names and recipe ingredients, but it does not disclose result ordering, pagination behavior, or what happens when no filters are provided.
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 concise sentences with no filler. The core purpose is front-loaded, and the additional matching behavior earns its place. Formatting is clean and easy to parse.
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 is a simple, filterable search with fully documented parameters, an output schema, and read-only annotations. The description is adequate for correct invocation. It would be slightly stronger if it explicitly directed users to get_recipe for retrieving a specific meal's full details.
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 100%, so the schema already documents every parameter. The description lists the main filter dimensions, which aligns with the schema, but it does not add any meaning beyond what the schema already provides. A baseline of 3 is appropriate.
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 states a specific verb ('Search'), a clear resource ('NoshUp's recipe catalogue'), and the search dimensions (cuisine, dietary preference, ingredient, meal type). It clearly differentiates from siblings like get_recipe and get_flyer_deals by focusing on catalogue-wide search.
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 conveys that this tool is for finding meals by multiple criteria, which gives clear context for when to use it. It does not explicitly name alternatives or say when not to use it, but the search-oriented phrasing and sibling names make the intended usage reasonably obvious.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_meals1 field changedInput schema / properties / cuisine / enumPrevious value: -[
- "indian",
- "italian",
- "mediterranean",
- "mexican",
- "east_asian",
- "french",
- "generic"
-]New value: +[
+ "indian",
+ "italian",
+ "mediterranean",
+ "mexican",
+ "east_asian",
+ "french",
+ "north_american",
+ "generic"
+]search_meals1 field changedInput schema / properties / cuisine / enumPrevious value: -[
- "indian",
- "italian",
- "mediterranean",
- "mexican",
- "east_asian",
- "french",
- "north_american",
- "generic"
-]New value: +[
+ "indian",
+ "italian",
+ "mediterranean",
+ "mexican",
+ "east_asian",
+ "french",
+ "generic"
+]search_meals1 field changedInput schema / properties / cuisine / enumPrevious value: -[
- "indian",
- "italian",
- "mediterranean",
- "mexican",
- "east_asian",
- "french",
- "generic"
-]New value: +[
+ "indian",
+ "italian",
+ "mediterranean",
+ "mexican",
+ "east_asian",
+ "french",
+ "north_american",
+ "generic"
+]get_flyer_dealsget_recipesearch_mealsGrocery meal planning, budgets, and flyer deals for Canadian households. Auth required.
Signed US food & grocery data: Kroger prices, nutrition, allergens, recalls, diet filters.
Danish grocery catalog as MCP tools: live offers across all major chains, stores, EAN lookup, stock.
Spoonacular food API: recipes, nutrition, ingredients, meal plans. Free 150/day.