Skip to main content
Glama
chrischall

skylight-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

skylight_plan_meal

Plan a meal for a specific date, set recurring schedules, link a recipe, and add ingredients to your grocery list.

Instructions

Plan a meal on a date (optionally repeating, link a recipe, add to grocery list).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateYesYYYY-MM-DD the meal is planned for.
noteNo
rruleNoiCal RRULE string for a repeating meal, e.g. "FREQ=DAILY;INTERVAL=1;UNTIL=20260626T235959Z" (meals use a plain rrule string, NOT an array).
frameIdNo
summaryYesMeal name. LIVE-VERIFIED: when meal_recipe_id is set, this must be BLANK — pass "" and the sitting inherits its name from the linked recipe. Sending a non-blank summary together with a recipe id returns 422 {"errors":{"summary":["must be blank"]}}.
descriptionNoIngredients / instructions.
meal_recipe_idNoLink an existing recipe.
saveToRecipeBoxNo
meal_category_idYesMeal category id (breakfast/lunch/dinner — from skylight_list_meal_categories).
add_to_grocery_listNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.1
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed1 schema field changedv0.8.1
    • changedInput schema / properties / summary / description
      Previous value: -"Meal name."New value: +"Meal name. LIVE-VERIFIED: when meal_recipe_id is set, this must be BLANK — pass \"\" and the sitting inherits its name from the linked recipe. Sending a non-blank summary together with a recipe id returns 422 {\"errors\":{\"summary\":[\"must be blank\"]}}."
  3. Changed4 schema fields changedv0.7.1
    • removedInput schema / properties / meal_category_id / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
    • addedInput schema / properties / meal_category_id / type
      Added value: +[
+  "string",
+  "number"
+]
    • removedInput schema / properties / meal_recipe_id / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
    • addedInput schema / properties / meal_recipe_id / type
      Added value: +[
+  "string",
+  "number"
+]
  4. First observedv0.4.6

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already mark the operation as non-read-only and non-destructive, and the description adds context about optional repeating, recipe linking, and grocery-list behavior. It does not disclose side effects such as whether planning a meal overrides an existing meal, whether confirmation is returned, or whether grocery-list creation is appended versus replacing, but these gaps are minor given the annotation coverage.

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?

The description is a single, efficient sentence front-loading the primary action and the optional features with no filler. It is appropriately concise for a tool whose parameter details and live-verified rules are already documented in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 10 parameters, 3 required, and no output schema, the description is too sparse to be fully self-sufficient. It doesn't explain how the agent should obtain meal_category_id, what the response indicates on success or failure, how the summary/recipe conflict works, or what happens when repeating/rrule is used, so the agent must rely heavily on the schema and external knowledge.

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 60% (6 of 10 parameters described). The description's references to 'repeating', 'link a recipe', and 'add to grocery list' map directly to rrule, meal_recipe_id, and add_to_grocery_list, adding little semantic value beyond the schema. Parameters like frameId, note, saveToRecipeBox, and description remain without explanatory context in the description, so it doesn't compensate for the uncovered portion.

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 uses a specific verb and resource ('Plan a meal on a date') and lists optional capabilities (repeating, link a recipe, add to grocery list). It clearly distinguishes this create-style action from sibling tools like skylight_update_meal, skylight_delete_meal, and bulk-oriented skylight_generate_meal_plan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the action verb and resource: call this when the agent needs to create a single meal plan entry. However, the description does not explicitly state when NOT to use it, nor does it differentiate itself from skylight_generate_meal_plan or skylight_add_recipe_to_grocery_list, leaving the agent to infer the boundary.

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

Deploy Server

Other Tools