skylight-mcp

skylight_generate_meal_plan

Generate an AI meal plan for selected dates, creating draft meal sittings asynchronously; poll the auto-creation intent and approve to finalize.

Instructions

Generate an AI meal plan for the given dates (creates draft meal sittings — async; poll with skylight_get_auto_creation_intent, then approve).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "meal_category_id": "<meal_category_id>",
      "dates": "<dates>"
    },
    "name": "skylight_generate_meal_plan"
  }
}

Input Schema

Name	Required	Description
`dates`	Yes	YYYY-MM-DD dates to generate meals for.
`frameId`	No
`recipe_source`	No	Defaults to 'generate' (AI-generated).
`mouths_to_feed`	No	How many people to feed.
`meal_category_id`	Yes	Meal category id (from skylight_list_meal_categories).
`add_to_grocery_list`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.1Sep 19, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Changed2 schema fields changedv0.7.1Aug 29, 2026
- removedInput schema / properties / meal_category_id / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
```
- addedInput schema / properties / meal_category_id / type
```
Added value: +[
+  "string",
+  "number"
+]
```
First observedv0.4.6Jul 30, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already flag a non-read-only, open-world, non-destructive operation; the description usefully adds that output is drafts created asynchronously plus the required poll/approve follow-up. It doesn't mention permission requirements or whether regenerating overwrites prior drafts.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that carries purpose, async behavior, and the follow-up tool chain with no 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 no output schema, the description adequately covers the async lifecycle by naming the polling and approval tools. Minor gaps remain around the undocumented frameId and add_to_grocery_list parameters.

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 coverage is 67%, and the description adds nothing about parameters beyond implying dates. Two parameters (frameId, add_to_grocery_list) lack descriptions in both schema and description, and the description doesn't explain the AI-vs-recipe source semantics the schema only hints at.

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?

States a specific verb (Generate) and resource (AI meal plan for given dates) and clarifies it creates draft meal sittings rather than final meals. This distinguishes it from skylight_plan_meal and other meal siblings.

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?

Explicitly describes the workflow context: async draft creation, then polling with skylight_get_auto_creation_intent, then approval. It does not, however, state when to prefer this over skylight_plan_meal (manual planning), so the alternative-selection guidance is incomplete.

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

Deploy Server