Skip to main content
Glama
chrischall

resy-mcp

by chrischall

resy_book

Destructive

Book a Resy restaurant reservation. Returns a dry-run preview with exact slot and card unless confirm:true is passed, then books the table. Target a specific time or accept the first available slot.

Instructions

Book a reservation. Composite tool: internally runs find-slots → get booking details → book. Confirm-gated: without confirm:true this returns a dry-run preview (venue, date, party size, the exact slot time that would be booked, and the payment card last-4) and books nothing. Pass desired_time (HH:MM, 24-hour) to target a specific slot. If your exact desired_time is not available the tool does NOT auto-book a different time — it returns the available times so you can pick, unless you pass allow_closest_time:true. Omit desired_time to take the first available slot. Uses the user's default payment method unless payment_method_id is supplied.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
latNo
lngNo
dateYesYYYY-MM-DD
confirmNoMust be true to proceed. Without this, the tool returns a preview.
venue_idYes
party_sizeYes
desired_timeNoHH:MM (24h)
payment_method_idNo
allow_closest_timeNoWhen true, if your exact desired_time is unavailable the closest slot is booked instead of returning the available times to pick from. Default false: an unavailable desired_time never silently books a different time.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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"
  2. Changed2 schema fields changedv0.5.4
    • addedInput schema / properties / allow_closest_time
      Added value: +{
      +  "description": "When true, if your exact desired_time is unavailable the closest slot is booked instead of returning the available times to pick from. Default false: an unavailable desired_time never silently books a different time.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / confirm
      Added value: +{
      +  "description": "Must be true to proceed. Without this, the tool returns a preview.",
      +  "type": "boolean"
      +}
  3. First observedv0.5.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already signal mutation (destructiveHint=true), but the description adds critical non-obvious behavior: without confirm:true it is a dry-run and books nothing, and an unavailable desired_time never silently books a different time. These details go beyond what annotations or schema convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence adds operational value: purpose, internal pipeline, confirm gate, time targeting, fallback rule, and payment default follow in logical order. It is dense but not bloated or repetitive.

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?

With no output schema, the description specifies the dry-run preview contents and the unavailable-time response. It does not explicitly state the confirmed-booking success payload or failure cases, but the essential call-control and safety behavior 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 description coverage is only 44%, so the description carries real weight. It clarifies confirm (preview vs actual), desired_time (target a specific slot), allow_closest_time (fallback semantics), and payment_method_id (defaults). Optional lat/lng remain undocumented, but the core booking parameters are well explained.

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 'Book a reservation' – a specific verb and resource – and expands with a composite pipeline (find-slots → get booking details → book). This clearly distinguishes it from siblings like resy_find_slots or resy_cancel.

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?

Explains confirm-gated dry-run mode, how desired_time and allow_closest_time interact, and the default payment method behavior. It does not explicitly name sibling alternatives, but the composite workflow and fallback semantics make when-to-use clear.

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