skylight-mcp

skylight_delete_meal

Destructive

Delete a planned meal from a Skylight meal plan by occurrence, this-and-future, or the whole series; broader deletions require confirmation and cannot be undone.

Instructions

Remove a planned meal (meal sitting) from the meal plan. Deletes one occurrence, this-and-future occurrences, or the whole series depending on apply_to (omit apply_to for a one-time meal). There is no undo. apply_to 'future' or 'all' asks the user to confirm first: a confirmation prompt where the client supports one; otherwise the first call returns a preview of exactly what would be deleted and a confirmToken, and only a repeat call with that token proceeds (see MCP_CONFIRM_MODE). apply_to 'one' (or omitted) deletes directly.

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": {
      "id": "<id>",
      "instance_date": "<instance_date>"
    },
    "name": "skylight_delete_meal"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Meal sitting id (from skylight_list_meals).
`frameId`	No
`apply_to`	No	Recurrence scope for a RECURRING meal (one with an `rrule` in skylight_list_meals): 'one' = just this occurrence (splits it out of the series), 'future' = this and all later occurrences (splits the tail into a new sitting), 'all' = the whole series. Omit for a one-time meal (`rrule: null`) — Skylight rejects apply_to there; if one is sent anyway the call is retried without it.
`confirmToken`	No	ONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 "confirmation-required" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.
`instance_date`	Yes	YYYY-MM-DD of the occurrence to act on — must be one of that sitting's `instances`.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.4.8Nov 3, 2026

changedInput schema / properties / apply_to / description

Previous value: -"Recurrence scope: 'one' = just this occurrence (splits it out of the series), 'future' = this and all later occurrences (splits the tail into a new sitting), 'all' = the whole series."New value: +"Recurrence scope for a RECURRING meal (one with an `rrule` in skylight_list_meals): 'one' = just this occurrence (splits it out of the series), 'future' = this and all later occurrences (splits the tail into a new sitting), 'all' = the whole series. Omit for a one-time meal (`rrule: null`) — Skylight rejects apply_to there; if one is sent anyway the call is retried without it."

changedInput schema / required

Previous value: -[
-  "id",
-  "instance_date",
-  "apply_to"
-]New value: +[
+  "id",
+  "instance_date"
+]

Changed2 schema fields changedv1.3.0Sep 25, 2026

removedInput schema / properties / confirm

Removed value: -{
-  "description": "Must be true to proceed. Without this, the tool returns a preview.",
-  "type": "boolean"
-}

addedInput schema / properties / confirmToken

Added value: +{
+  "description": "ONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 \"confirmation-required\" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.",
+  "type": "string"
+}

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"

Addedv0.8.1Aug 31, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true, but the description adds critical context beyond them: there is no undo, the confirmation requirement for 'future'/'all', and the exact two-step fallback (preview plus confirmToken, governed by MCP_CONFIRM_MODE). This is exactly the behavioral detail an agent needs before an irreversible write.

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

Conciseness4/5

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

Front-loaded with purpose, then scope, then the confirmation protocol. It is dense with parentheticals and forward references (MCP_CONFIRM_MODE), but nearly every clause carries necessary safety information for a destructive mutation.

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

Completeness5/5

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

No output schema exists, yet the description explains what the confirmation-phase response contains (a preview of exactly what would be deleted and a confirmToken). Combined with the destructive annotations, an agent has everything needed to invoke this safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 80%, so most parameters are already documented; the description reinforces apply_to semantics and explains when confirmToken is expected. The only uncovered parameter, frameId, gets no mention in either place, which is the remaining gap.

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 and resource ('Remove a planned meal (meal sitting) from the meal plan') and immediately clarifies the three deletion scopes. An agent can distinguish this from skylight_update_meal or skylight_delete_recipe without opening any schema.

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?

Gives explicit conditions for each mode: omit apply_to for a one-time meal, and 'one' deletes directly while 'future'/'all' require confirmation. It does not name an alternative tool (e.g. update skylight_update_meal to edit instead of delete), so it stops short of full when/when-not routing.

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

Deploy Server