Skip to main content
Glama

Validate a Nexez booking

nexez_validate_booking
Read-only

Dry-run one appointment booking. Checks the time against the seller's rules and says plainly why a time is refused, with the next open times. Checks the details and answers. On success returns approvalCard: every line that would be sent, including each answer, who gave it, and the note. Show the buyer the whole card and get their approval before using the returned handoff. Never books, holds a time, or contacts the seller. Free services only: a paid service returns the booking link for the buyer to finish themself.

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": {
      "slug": "<slug>",
      "service": "<service>",
      "start": "<start>",
      "details": "<details>"
    },
    "name": "nexez_validate_booking"
  }
}

Input Schema

NameRequiredDescriptionDefault
linkNoOptional https web address for the seller to look at (a listing, an album, a document). Only when nexez_booking_options lists link under alsoAsks. Shown to the seller as text.
noteNoOptional plain-text note for the seller, up to 1,000 characters. It is stored as written by the assistant for the buyer, and the buyer must see it in the approval card. No Social Security, card, bank or wiring details.
slugYesExact published listing slug.
startYesStart time as an ISO instant taken from nexez_booking_options, for example 2026-11-12T16:30:00.000Z. Do not invent a time.
addressNoWhere the appointment happens, as the buyer said it. Required when alsoAsks lists address. Never guess it.
answersNoAnswers to the seller's questions, keyed by question id from nexez_booking_options. For a choice question use one of its options exactly.
detailsYesThe buyer's own details. Never invent them.
serviceYesService id from nexez_booking_options.
languageNoThe buyer's preferred language, only when alsoAsks lists language and the buyer said it.
accessibilityNoWhat the buyer said they need to take part, in their words, only when alsoAsks lists accessibility. Never infer it.
buyerAnsweredNoIds of the questions the buyer answered themself in this conversation. A question with assistantMayAnswer false is accepted only when its id is listed here.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / accessibility
      Added value: +{
      +  "description": "What the buyer said they need to take part, in their words, only when alsoAsks lists accessibility. Never infer it.",
      +  "type": "string"
      +}
    • addedInput schema / properties / address
      Added value: +{
      +  "description": "Where the appointment happens, as the buyer said it. Required when alsoAsks lists address. Never guess it.",
      +  "type": "string"
      +}
    • addedInput schema / properties / language
      Added value: +{
      +  "description": "The buyer's preferred language, only when alsoAsks lists language and the buyer said it.",
      +  "type": "string"
      +}
    • addedInput schema / properties / link
      Added value: +{
      +  "description": "Optional https web address for the seller to look at (a listing, an album, a document). Only when nexez_booking_options lists link under alsoAsks. Shown to the seller as text.",
      +  "type": "string"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and destructiveHint=false, yet the description adds substantive behavior: no booking, no hold, no seller contact, paid services return a link instead of a card, refusal responses include next open times, and the card enumerates every line sent including answer provenance and the note. These are real operational traits not encoded in any structured field.

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?

It leads with the one-line purpose and proceeds in a logical order: what it checks, what it returns, what the agent must do with it, and what it never does. The free-services caveat arrives late as a trailing sentence and could be grouped with the refusal behavior, but no sentence is 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?

For an 11-parameter tool with nested objects and no output schema, the description still covers the success return (approvalCard contents), the failure return (plain refusal reason plus next open times), side-effect boundaries, and prerequisites for obtaining inputs. An agent has enough to call it correctly and interpret the result.

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 baseline is 3, but the description adds meaning beyond the schema by tying note and answers to the approval card the buyer must see, and by flagging the free-services-only constraint that affects which parameters matter. It does not explain buyerAnswered or accessibility semantics in prose, so it is not fully additive.

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?

"Dry-run one appointment booking" names a specific verb (dry-run/validate) and resource (one appointment booking), immediately distinguishing it from nexez_booking_options (which supplies the inputs) and from the other validate_* siblings. It also scopes it as a single booking, not a batch.

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?

The description gives clear workflow context: take slug/service/start from nexez_booking_options, show the buyer the approvalCard, and get approval before using the handoff. It stops short of explicitly naming what to call instead once the buyer approves (i.e., no direct contrast with nexez_validate_checkout or the actual booking path), so the alternatives are implied rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources