Skip to main content
Glama
chrischall

skylight-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

skylight_import_events_from_photo

Destructive

Import calendar events from a photo of a flyer or schedule. AI extracts details, then you confirm before the events are added.

Instructions

Import calendar events from a photo of a flyer/invite/schedule using Skylight's AI (event_importer). Best-effort/UNVERIFIED: uploads the photo to S3 then posts an event_importer intent that references the latest upload (the server-side photo↔intent link is inferred from captured traffic, not confirmed). 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). The preview echoes the resolved absolute image_path, detected mime and size, and nothing is read or uploaded until it is confirmed. Poll skylight_get_auto_creation_intent / skylight_list_auto_creation_drafts, then skylight_approve_auto_creation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
frameIdNo
image_pathYesAbsolute path to a local image of the events to import (same types and 200 MiB cap as skylight_upload_photo).
category_idsNoFamily-member category ids to assign the imported events to.
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.

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 changedv1.1.3
    • changedInput schema / properties / image_path / description
      Previous value: -"Absolute path to a local image of the events to import."New value: +"Absolute path to a local image of the events to import (same types and 200 MiB cap as skylight_upload_photo)."
  3. 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"
  4. 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"
+]
  5. First observedv0.4.6

TDQS

A4.3/5.0
Behavior5/5

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

The description goes well beyond the annotations, disclosing best-effort/UNVERIFIED status, the inferred photo-to-intent link, the two-step confirmation flow, the preview fields, and that nothing is read or uploaded until confirmed. This is precisely the safety-relevant behavior an agent needs and annotations cannot express.

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 description is front-loaded with purpose and densely packs necessary caveats: unverified results, confirmation mechanics, and polling/approval steps. It is long, but each sentence earns its place for a complex, side-effect-heavy tool; minor tightening would still be possible.

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 complex tool with no output schema, the description covers the side-effect model, confirmation behavior, preview contents, and follow-up actions. It does not fully describe the final success return shape or clarify frameId, so it is strong but not fully exhaustive.

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 75%, and image_path, category_ids, and confirmToken are already well documented in the schema. The description adds little new parameter-level meaning beyond mentioning that the preview echoes image_path/mime/size; frameId remains undocumented in both schema and description.

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 opens with a specific verb and resource: 'Import calendar events from a photo of a flyer/invite/schedule using Skylight's AI (event_importer).' This clearly distinguishes it from siblings like skylight_upload_photo (upload only) and skylight_create_event (manual creation).

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?

It provides clear context: use this when a photo contains calendar events and needs AI extraction. It also gives the follow-up workflow (poll intent/drafts, then approve). It does not explicitly state when-not cases or name alternatives like skylight_create_event for manual input, so it stops short of a 5.

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