Skip to main content
Glama
chrischall

skylight-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

skylight_update_meal

Destructive

Change a planned meal's name, recipe, slot, notes, date, or repeat rule for one occurrence, then choose whether to apply the edit to one, future, or all sittings.

Instructions

Update a planned meal (meal sitting) — change its name, recipe, category/slot, notes, date or repeat rule. Targets one occurrence by its date and applies the change at the chosen recurrence scope. For a recurring meal, note that apply_to:'one' and 'future' SPLIT the series into additional sittings rather than editing in place; re-run skylight_list_meals afterward to see the resulting shape. 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 and a confirmToken, and only a repeat call with that token proceeds (see MCP_CONFIRM_MODE).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesMeal sitting id (from skylight_list_meals).
dateNoYYYY-MM-DD to move the meal to.
noteNo
rruleNoReplacement iCal RRULE string (plain string, NOT an array).
frameIdNo
summaryNoNew meal name. The create route 422s when this is non-blank and meal_recipe_id is also set; whether PATCH enforces the same rule is UNVERIFIED, so prefer setting one or the other.
apply_toYesRecurrence 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.
descriptionNoIngredients / instructions.
confirmTokenNoONLY 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_dateYesYYYY-MM-DD of the occurrence to act on — must be one of that sitting's `instances`.
meal_recipe_idNoLink a different recipe.
meal_category_idNoMove to another slot (breakfast/lunch/dinner).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.3.0
    • 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"
+}
  2. 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"
  3. Addedv0.8.1

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial behavior beyond the destructiveHint/openWorldHint annotations: 'one'/'future' splits the series rather than editing in place, and future/all trigger a confirmation prompt with a preview + confirmToken fallback (MCP_CONFIRM_MODE). This is exactly the kind of side-effect disclosure an agent needs before a destructive call.

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 verb+resource and mutable fields, then escalation/confirmation rules. Dense but each sentence carries real information; the confirmation-fallback sentence is long but necessary for correct invocation.

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?

For a 12-param destructive mutation with no output schema, the description covers the risky surfaces (recurrence scope, confirmation, series splitting). Minor gaps remain around undocumented params like frameId, but the critical behavioral contract is present.

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?

With 83% schema coverage the schema already documents most params, but the description still adds value by grouping the editable fields and explaining apply_to's split-vs-edit behavior. It does not, however, clarify frameId or the summary/meal_recipe_id conflict beyond what the schema states.

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?

Opens with a specific verb+resource ('Update a planned meal (meal sitting)') and enumerates the mutable fields, immediately separating it from skylight_plan_meal, skylight_delete_meal and skylight_update_recipe. An agent knows exactly what object is being mutated.

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?

Explains targeting semantics (one occurrence by date, scope via apply_to) and prescribes a follow-up (re-run skylight_list_meals to observe the resulting shape). It stops short of naming explicit alternative tools or when-not-to-use conditions, but the operational context is clear.

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