Skip to main content
Glama
Sign In

KeyFlight PNR Converter

by io.keyflight
OverviewDiscussionsAdmin

Make a PRO ticket PDF

make_ticket

Make a PRO e-ticket PDF (Expedia style: PNR, airline logos, class, optional price) from a raw PNR and return a link to the PDF. Passenger names and the PNR code come from the text unless given here. Included in the KeyFlight subscription.

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": {
      "text": "<text>"
    },
    "name": "make_ticket"
  }
}

Input Schema

NameRequiredDescriptionDefault
pnrNoBooking code printed on the ticket, 5–8 letters and digits. Default: the one in the text, or a random one.
logoNoLogo in the ticket header. Default: none.
textYesThe PNR as shown by the GDS (Amadeus, Sabre, Galileo/Apollo, Worldspan), up to 20000 characters.
priceNoTotal price printed on the ticket, e.g. "1200.50". Default: no price on the ticket.
currencyNoCurrency next to the price, e.g. "USD", "€". Default: "$".
passengersNoPassenger names as on the ticket, e.g. "SMITH/JOHN MR". Default: the names in the PNR.
date_formatNo"short" or "numeric".
time_formatNo24 or 12 hour time. Default: 24.
booking_classNoDefault: the cabin of the first flight's booking class.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the bar is lower. The description contributes the return type (link to a PDF) and the subscription gating, but omits whether links expire, whether repeated calls with the same PNR mint new tickets, or what happens if the text can't be parsed.

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?

Three tight sentences, front-loaded with the action and output before the fallback/default behavior. Nothing is padded, though the subscription remark sits slightly outside the operational core.

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 carries the return value and does so ('return a link to the PDF'), and all nine parameters are covered by the schema. The remaining gaps – link lifetime, latency, and failure modes for unparseable GDS text – are real but modest for a formatting tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all nine parameters are already documented, including defaults and enums. The description's one substantive addition is the precedence rule ('names and PNR come from the text unless given here'), which the schema states only per-field; beyond that it does not explain date_format, which the schema leaves undescribed.

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 (make a PRO e-ticket PDF) plus concrete content (PNR, airline logos, class, optional price) and the return value (a link to the PDF). The output-oriented framing cleanly separates it from the sibling decode_pnr, which parses rather than generates.

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

Usage Guidelines3/5

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

Usage is only implied by 'from a raw PNR', which tells an agent the input is GDS text. There is no explicit statement of when to call this versus decode_pnr, no prerequisites, and no exclusions – the subscription sentence is commercial, not guidance.

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

All KeyFlight PNR Converter toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources