SetLuca

Official

by setluca

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Move a call to a new time

luca_reschedule_call

Destructive

Instructions

Move a booked call to a new time and hand back a fresh reschedule link for the lead. Checks the new slot is open first, against the schedule of its booking type when it has one, and returns the open slots instead of moving the call when it is taken. A call with an idempotencyKey skips that check so a retry gets the original result back. A manual booking moves in SetLuca only. A Cal.com or Google Calendar booking moves on that calendar too, but only once the provider confirms: until then the booking's operation.state reads pending_provider and it keeps its old time, so read the booking again before telling the coach the call moved. A Calendly, GoHighLevel or iClosed booking is refused so the coach can move it with the provider, and so is a provider booking with no calendar event, such as one recorded with luca_bookings_create. Moving the call re-arms the lead's reminder for the new time, so pass confirm: true only after the coach approves the move. Example: call with { bookingId, slotAt: "2026-07-16T15:00:00Z", confirm: true } after the lead asked to push the call. SetLuca sends the lead no DM about the move, but a Google Calendar booking's calendar emails the lead the updated invite, and Cal.com may too. Send the lead the link yourself, or draft the message through the review queue.

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": {
      "bookingId": "<bookingId>",
      "slotAt": "<slotAt>"
    },
    "name": "luca_reschedule_call"
  }
}

Input Schema

Name	Required	Description
`slotAt`	Yes	ISO-8601 start time to move the call to, with an offset.
`confirm`	No	This tool has a real-world side effect: it messages real leads, books, moves, or cancels a call, changes a lead's consent, imports leads, writes to a connected calendar or CRM, sends workspace events to an outside URL, or re-triggers downstream automations. Pass confirm: true to proceed; the call is rejected without it.
`provider`	No	The coach's booking provider. Used only for the availability check, and only when the booking has no booking type. The booking keeps the provider it already has. Pass it when the coach is not on Calendly, or the availability check reads the wrong calendar.
`bookingId`	Yes	The booking to move.
`workspaceId`	No	Optional Luca workspace id override.
`workspaceSlug`	No	Optional Luca workspace slug override.
`expiresInHours`	No	How long the new reschedule link stays usable. Defaults to 168 hours.
`idempotencyKey`	No	Reuse the same key when retrying this exact reschedule. A keyed call skips the availability check and lets the API replay the first result.

Output Schema

Name	Required	Description	Default
`result`	Yes
`provenance`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.0Oct 21, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the destructiveHint/openWorldHint annotations: discloses the availability check and re-arming of the lead's reminder, the pending_provider state that leaves the old time in place until provider confirmation, the instruction to re-read the booking, and the fact that SetLuca sends no DM while Google Calendar/Cal.com may email the lead.

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?

Dense but front-loaded: the move-and-return-a-link purpose leads, then edge cases follow. Some of it is long-form block text (provider-by-provider refusal list plus the DM/calendar-email caveat) that could be tightened, though most sentences carry distinct operational information.

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?

For a destructive, open-world mutation with 8 params, it covers the failure paths (slot taken returns slots), async provider confirmation, provider refusals, and the messaging side effects. An output schema exists, so return-value detail is not required.

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 100%, so the schema carries the baseline. The description still adds policy the schema does not: pass confirm: true only after coach approval, and idempotencyKey retries skip the availability check and replay the original result. A worked example with bookingId and slotAt anchors usage.

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 ('Move a booked call to a new time') and adds the secondary outcome ('hand back a fresh reschedule link for the lead'). This clearly separates it from siblings like luca_bookings_update, luca_bookings_cancel and luca_book_call.

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

Usage Guidelines5/5

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

Explicitly covers when the tool applies per provider (manual moves in SetLuca, Cal.com/Google move on the calendar, Calendly/GoHighLevel/iClosed are refused), names a concrete alternative for one case ('such as one recorded with luca_bookings_create'), and conditions confirm on coach approval.

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

Deploy Server