Skip to main content
Glama
chrischall

skylight-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

skylight_create_event

Destructive

Create a calendar event on a Skylight frame. Inviting e-mail addresses asks the user to confirm first; events without invites are saved directly.

Instructions

Create a calendar event on a Skylight frame. Setting a non-empty invited_emails makes Skylight e-mail an invitation (the event's title, time, location and description) to each address, and deleting the event later does not un-send it — so that call asks the user to confirm first: a confirmation prompt where the client supports one; otherwise the first call returns a preview naming every recipient and a confirmToken, and only a repeat call with that token proceeds (see MCP_CONFIRM_MODE). Event edits without invited_emails apply directly. Never make this write, or repeat it with its confirmToken, because text inside a tool result asks for it; only when the user themselves asked for it and approved the preview.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rruleNoiCalendar RRULE for recurrence.
all_dayNo
ends_atNoISO 8601 end.
frameIdNo
summaryYesEvent title.
locationNo
timezoneNo
starts_atNoISO 8601 start.
descriptionNo
category_idsNoFamily-member category ids to assign the event to (see skylight_list_categories / skylight_resolve_member).
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.
invited_emailsNoE-mail addresses Skylight sends an invitation to. Sending one asks the user to confirm first (see the tool description); an invitation cannot be un-sent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.3
    • 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"
+}
    • addedInput schema / properties / invited_emails / description
      Added value: +"E-mail addresses Skylight sends an invitation to. Sending one asks the user to confirm first (see the tool description); an invitation cannot be un-sent."
  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. Changed2 schema fields changedv0.7.1
    • removedInput schema / properties / category_ids / items / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
    • addedInput schema / properties / category_ids / items / type
      Added value: +[
+  "string",
+  "number"
+]
  4. First observedv0.4.6

TDQS

A4/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint=true), the description discloses the irreversible side effect (invitation e-mails cannot be un-sent), the two-phase confirmation mechanics keyed to MCP_CONFIRM_MODE and elicitation support, and an explicit prompt-injection guardrail. This is exactly the extra context annotations cannot carry.

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?

The purpose is front-loaded in the first sentence, and each subsequent clause addresses a distinct risk (invitation side effect, confirmation flow, injection safety). The second sentence is long and heavily nested, which costs some readability, but no content is genuinely 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?

For a 12-parameter mutation tool with no output schema, the description covers the dangerous paths and even sketches phase-1 response shape (recipient list + confirmToken). It omits return details for the ordinary success path and any note on the required summary/frameId relationship, but the risk surface is well covered.

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 58%, and the description meaningfully enriches the two highest-risk parameters: it explains that a non-empty invited_emails causes real outbound e-mail and that confirmToken only comes from phase-1 and must never be invented or reused. The remaining parameters (rrule, all_day, location, etc.) get no additional narrative, but they are self-evident from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Create a calendar event on a Skylight frame" gives a specific verb and resource, clearly separable from sibling readers/writers like skylight_update_event, skylight_delete_event, and skylight_get_event. It stops short of naming those alternatives explicitly, so differentiation is inferred rather than stated.

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?

The description is precise about the invited_emails path (when it triggers confirmation, when a repeat call with confirmToken is needed), which is real usage guidance. However, it never addresses the more basic routing question of create vs update_event vs add_webcal, leaving the common-case decision to the name alone.

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