Skip to main content
Glama

Timeplex K-Beauty Booking

by ai.timeplex

start_booking

Read-onlyIdempotent

Create a pre-filled Timeplex booking link (and booking card) for a selected Korean beauty or wellness shop and appointment. Use this after the user has selected or clearly identified a specific shop. A bare category request with no shop chosen and no area or date given ("recommend a scrub shop") is NOT a selection — ask for the area and the booking conditions first instead of calling this tool. This tool does not create or confirm a reservation — it only generates a booking link. Never ask "shall I create a link?". Once a specific shop has been selected or clearly identified, call this tool and include the link in your reply. Date, time and items are all optional — if the customer has not picked them yet, still call it with just the shop; they choose the rest on the booking page. Never withhold the link just to ask for a date, time, or service first. Put link_markdown into your reply as-is — never expose the raw URL. Briefly relay the returned guidance and note to the customer, always in the language the user used, starting with the response's reply_header line. Describe the effect of payment as the time being temporarily secured (Korean: 임시 확보) — never as winning a race or claiming it first (Korean: 선점), and never imply the booking is already complete.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoYYYY-MM-DD (Asia/Seoul). Optional — omit if the customer has not picked a date; they choose it on the booking page.
slugYesShop slug returned by search_shops.
timeNoHH:MM. Optional — omit if the customer has not picked a time.
itemsNoOptional — omit if no service is chosen yet. Follow the booking_model returned by get_shop_services: use resource_id for designated-staff shops and qty for capacity-based shops. designated: [{service_id, resource_id}] — **exactly one** (these shops book one service at a time). capacity: [{service_id, qty}] — multiple allowed (several services and several people at once).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoHow the slot is secured and finally confirmed — mention this to the customer
summaryNoWhat is preselected on the booking page.
guidanceNoCustomer-facing summary of the remaining steps — keep it light and pass it on
confirmedYesAlways false — nothing is booked by this tool
link_labelNo
next_stepsNoWhat the customer does after opening the link (contact info, payment, shop-owner approval)
booking_urlYesPrefilled booking page (customer completes contact info + payment there)
reply_headerNo
link_markdownYesPut this into the reply as-is (never expose the raw URL)
reply_header_usageNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed5 schema fields changed
    • changedInput schema / properties / items / description
      Previous value: -"Optional — omit if no service is chosen yet. Hair: [{service_id, resource_id}] — **exactly one** (hair shops book one service at a time). Massage: [{service_id, qty}] — multiple allowed (several services and several people at once)."New value: +"Optional — omit if no service is chosen yet. Follow the booking_model returned by get_shop_services: use resource_id for designated-staff shops and qty for capacity-based shops. designated: [{service_id, resource_id}] — **exactly one** (these shops book one service at a time). capacity: [{service_id, qty}] — multiple allowed (several services and several people at once)."
    • addedInput schema / properties / slug / description
      Added value: +"Shop slug returned by search_shops."
    • addedOutput schema / properties / guidance / description
      Added value: +"Customer-facing summary of the remaining steps — keep it light and pass it on"
    • addedOutput schema / properties / next_steps / description
      Added value: +"What the customer does after opening the link (contact info, payment, shop-owner approval)"
    • addedOutput schema / properties / note / description
      Added value: +"How the slot is secured and finally confirmed — mention this to the customer"
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "booking_url": {
+      "description": "Prefilled booking page (customer completes contact info + payment there)",
+      "type": "string"
+    },
+    "confirmed": {
+      "description": "Always false — nothing is booked by this tool",
+      "type": "boolean"
+    },
+    "guidance": {
+      "type": "string"
+    },
+    "link_label": {
+      "type": "string"
+    },
+    "link_markdown": {
+      "description": "Put this into the reply as-is (never expose the raw URL)",
+      "type": "string"
+    },
+    "next_steps": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "note": {
+      "type": "string"
+    },
+    "reply_header": {
+      "type": "string"
+    },
+    "reply_header_usage": {
+      "type": "string"
+    },
+    "summary": {
+      "description": "What is preselected on the booking page.",
+      "properties": {
+        "currency": {
+          "type": "string"
+        },
+        "items": {
+          "items": {
+            "properties": {
+              "currency": {
+                "type": "string"
+              },
+              "duration_min": {
+                "type": [
+                  "integer",
+                  "null"
+                ]
+              },
+              "price": {
+                "type": [
+                  "number",
+                  "string",
+                  "null"
+                ]
+              },
+              "qty": {
+                "type": "integer"
+              },
+              "service": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "staff": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "shop": {
+          "type": "string"
+        },
+        "timezone": {
+          "type": "string"
+        },
+        "total_price": {
+          "type": "number"
+        },
+        "when": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "booking_url",
+    "link_markdown",
+    "confirmed"
+  ],
+  "type": "object"
+}
  3. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial context beyond that: it explicitly states '**This tool does not create or confirm a reservation — it only generates a booking link.**' It also details response handling—including link_markdown usage, relaying guidance in the user's language, and the correct payment wording ('temporarily secured' vs. 'winning a race'). This discloses behavioral traits and response constraints that annotations do not cover, and it does not contradict any annotation.

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 long but every sentence carries instructional weight, covering usage conditions, response formatting, and parameter handling. It is front-loaded with the core purpose and usage condition. Some redundancy exists in repeated 'never' statements, but these serve as explicit prohibitions rather than filler. The structure is clear, though a more condensed version could achieve the same effect with less repetition.

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?

Given the presence of an output schema, annotations, and full parameter descriptions, the description is nearly complete for an agent to call the tool correctly. It covers when to call, what it returns (link and guidance), how to present results, and parameter omissions. Minor gaps include handling of invalid slugs or shop not found, but these are typically covered by the output schema and common error handling. The description is robust enough for its complexity.

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?

The schema covers 100% of parameters with descriptive text (e.g., items explanation about designated vs. capacity). The description adds value by clarifying when to omit optional parameters ('if the customer has not picked them yet, still call it with just the shop') and reinforcing that slug must come from search_shops. It also reminds that date/time/items are optional and that the customer chooses them on the booking page, which goes beyond the schema's basic descriptions.

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: 'Create a pre-filled Timeplex booking link (and booking card) for a selected Korean beauty or wellness shop and appointment.' It clearly distinguishes itself from siblings by stating it only generates a link and does not create/confirm a reservation, which separates it from request_booking. The 'selected shop' condition differentiates it from search_shops and search_availability.

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?

The description gives explicit when-to-use and when-not-to-use guidance: 'Use this after the user has selected or clearly identified a specific shop' and contrasts with a bare category request that 'is NOT a selection — ask for the area and the booking conditions first.' It also instructs to never ask for permission, never withhold the link for missing date/time, and always call with just the shop if needed. This directly addresses alternative actions and conditions.

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

All Timeplex K-Beauty Booking toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation5/5

Each tool targets a distinct step in the booking workflow: searching shops, retrieving services, checking availability, initiating a booking, and handling manual requests for non-bookable shops. Their purposes and usage conditions are clearly separated with specific guidance on when to use each, eliminating ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case: get_shop_services, request_booking, search_availability, search_shops, start_booking. The verbs (get, request, search, start) and nouns (shop_services, booking, availability, shops) are all lowercase and underscore-separated, providing a predictable and readable naming scheme.

Tool Count5/5

With exactly 5 tools, the server is well-scoped for its purpose. It covers the essential phases of finding a shop, inspecting services, checking availability, and initiating bookings, without unnecessary expansion. This count is typical for a focused domain-specific MCP and each tool earns its place.

Completeness4/5

The tool set covers the primary booking flow comprehensively: search_shops, get_shop_services, search_availability, and start_booking handle the standard online-booking path, while request_booking covers shops that require manual concierge intervention. Minor gaps exist (e.g., no tool for canceling or modifying bookings), but since start_booking only generates a booking link and actual reservation management happens on the booking page, the surface is reasonably complete for its stated purpose.

Resources