Skip to main content
Glama
chrischall

opentable-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

opentable_book

Destructive

Books an OpenTable reservation using fresh slot hash and reservation token from opentable_find_slots; confirms card holds and cancellation policy before finalizing.

Instructions

Book an OpenTable reservation. Requires a fresh slot_hash + reservation_token from opentable_find_slots (tokens expire within minutes — call find_slots just before book). dining_area_id is OPTIONAL: when omitted it's auto-resolved to the default dining area from OpenTable's booking-details page, so find_slots → book works without a separate opentable_get_restaurant call. For CC-required slots (prime-time at busy restaurants), opentable_book refuses without a booking_token from opentable_book_preview — the preview step surfaces the cancellation policy and the saved card that would be held. Auto-fetches the user's profile (name/email/phone) from /user/dining-dashboard. Returns confirmation_number + security_token; save both — they're required to cancel. For Listing-type restaurants there's no slot to lock — callers should check opentable_get_restaurant.bookable first and surface the restaurant's phone/URL instead. 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; the prompt names the restaurant, the card that will be held and the cancellation policy (see MCP_CONFIRM_MODE).

Input Schema

NameRequiredDescriptionDefault
dateYesYYYY-MM-DD
timeYesHH:MM (24h) — must match the slot returned by find_slots
slot_hashYesslot_hash from opentable_find_slots
party_sizeYes
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.
booking_tokenNoOpaque token from opentable_book_preview. REQUIRED for CC-required slots (book will refuse otherwise). Optional for standard slots — when present, skips a redundant re-lock.
experience_idNoTamper-check signal for Experience tokens. When set, must match the experienceId baked into the booking_token by preview — agents that re-state the experience choice here get refused if it drifted from preview.
restaurant_idYes
dining_area_idNoOptional dining-area (room) id. When omitted, auto-resolved to the default dining area from the booking-details page — no opentable_get_restaurant call needed. Pass explicitly only to pin a specific room. Ignored on the booking_token path (the token already carries the resolved area).
experience_idsNoPass-through from find_slots.experience_ids. When non-empty, book refuses without a booking_token from opentable_book_preview.
database_regionNoOpenTable's sharded-database region for the restaurant. Defaults to 'NA' (North America). Pass the venue's region (e.g. for UK/EU/APAC restaurants) when booking or cancelling outside North America — slot-lock, availability, and cancel route to the wrong database shard, or fail opaquely, when this is wrong. LIMITATION: not auto-derived from restaurant data (OpenTable's availability/booking responses don't surface the shard id), so non-NA bookings must set it explicitly.
reservation_tokenYesslot_availability_token from opentable_find_slots

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.3.4
    • addedInput schema / properties / date / pattern
      Added value: +"^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$"
    • addedInput schema / properties / time / pattern
      Added value: +"^([01]\\d|2[0-3]):[0-5]\\d$"
  2. Changed2 schema fields changedv1.2.1
    • 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"
+}
  3. Changed1 schema field changedv1.0.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  4. First observedv0.14.3

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructive/non-idempotent/open-world, and the description adds substantial context beyond them: the two-phase confirmation flow (preview + confirmToken vs elicitation), auto-fetch of user profile, the returned confirmation_number + security_token that are required to cancel, refusal behavior when booking_token is missing, and the surfaced cancellation policy. This is exactly the extra behavioral detail 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?

Front-loaded with the primary action and its input dependencies, then flows into confirmation, returns, and edge cases in a sensible order. It is dense and long, but nearly every clause (token expiry, Listing restaurants, database_region caveat) carries actionable information rather than filler.

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?

No output schema exists, yet the description states the return payload (confirmation_number + security_token and that they are needed for cancel), documents the confirmation handshake across both client modes, and covers the non-slot Listing path. For a 12-param destructive tool, nothing an agent needs to invoke it correctly is missing.

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 83% (baseline 3), but the description adds workflow meaning: it explains why dining_area_id is optional (auto-resolved so find_slots → book needs no get_restaurant), when booking_token becomes mandatory, and how experience_ids/experience_id interact with preview. Some points duplicate the schema descriptions (confirmToken, database_region), keeping it from a 5.

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 ('Book an OpenTable reservation') and immediately distinguishes itself from siblings by naming the upstream tools (opentable_find_slots, opentable_book_preview) and the failure modes that route to them. An agent can tell this apart from opentable_modify/opentable_cancel without reading any schema.

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?

Gives explicit when-to-use mechanics: requires a fresh slot_hash + reservation_token, warns they expire within minutes so find_slots must be called just before, and states dining_area_id may be omitted because it auto-resolves. It also names preconditions for CC-required slots (booking_token from opentable_book_preview) and the Listing-type edge case (check opentable_get_restaurant.bookable instead).

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