ATA Travel

start_traveler_handoff

Internal approval step for quote or booking tools. Before calling, read guestEmail back to the traveler and confirm it is correct; then set emailConfirmedByTraveler=true. If an email is sent, tell the traveler only to check their inbox and click the secure ATA link. Do not mention handoffs/tool details to the traveler.

Input Schema

TableJSON Schema

Name	Required	Description
`action`	Yes	Use BOOKING_HOLD before creating a reservation; BOOKING_READ grants only read access to an existing booking for questions.
`adults`	No
`roomId`	No
`checkIn`	No
`quoteId`	No
`checkOut`	No
`children`	No
`agentName`	No	Agent/application display name when known.
`guestName`	Yes	Traveler name collected by the agent.
`quoteHash`	No
`guestEmail`	Yes	Traveler email. ATA sends the verification/approval link here.
`guestPhone`	No
`ratePlanId`	No
`mcpSessionId`	No	Optional client-side MCP/session correlation ID.
`agentProvider`	No	Agent platform or provider name when known.
`intentSummary`	No	Short traveler-facing summary of what ATA is verifying, without mentioning internal handoff/tool details.
`propertyToken`	No
`confirmationCode`	No	Required for BOOKING_READ: the ATA confirmation code printed on the booking confirmation.
`selectedRoomCount`	No
`emailConfirmedByTraveler`	No	Set true only after reading guestEmail back to the traveler and they confirm it is correct.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 8, 2026

changedInput schema / properties / action / description

Previous value: -"The action the traveler is being asked to approve. Use BOOKING_HOLD before create_provisional_booking."New value: +"Use BOOKING_HOLD before creating a reservation; BOOKING_READ grants only read access to an existing booking for questions."

changedInput schema / properties / action / enum

Previous value: -[
-  "QUOTE",
-  "BOOKING_HOLD"
-]New value: +[
+  "QUOTE",
+  "BOOKING_HOLD",
+  "BOOKING_READ"
+]

addedInput schema / properties / confirmationCode

Added value: +{
+  "description": "Required for BOOKING_READ: the ATA confirmation code printed on the booking confirmation.",
+  "maxLength": 64,
+  "minLength": 1,
+  "type": "string"
+}

Changed1 schema field changedJul 9, 2026

changedInput schema / properties / intentSummary / description

Previous value: -"Short traveler-facing summary of what the agent is asking ATA to approve."New value: +"Short traveler-facing summary of what ATA is verifying, without mentioning internal handoff/tool details."

Changed1 schema field changedJul 8, 2026

addedInput schema / properties / emailConfirmedByTraveler

Added value: +{
+  "description": "Set true only after reading guestEmail back to the traveler and they confirm it is correct.",
+  "type": "boolean"
+}

First observedJun 29, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Given that annotations only indicate non-readOnly, non-destructive, non-idempotent, the description adds crucial transparency by revealing side effects: sending an email and setting the emailConfirmedByTraveler flag. It also clarifies the tool's internal nature, exceeding what annotations provide.

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?

The description is a single paragraph that conveys all essential instructions without redundancy. It is tightly worded and each sentence contributes operational guidance, making it efficient and easy to parse.

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?

While the description provides the core workflow and constraints, it does not elaborate on the broader context (e.g., what constitutes a 'handoff', how this fits with other tools, or expected inputs beyond the two mentioned). However, given the tool's focused purpose and the presence of a schema, the description is largely sufficient for an agent to execute correctly.

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

Parameters2/5

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

The description only clarifies the usage of guestEmail and emailConfirmedByTraveler, while many other parameters (e.g., action, checkIn, checkOut, quoteId, ratePlanId) remain unaddressed. With schema description coverage at 45%, the description does not sufficiently compensate for the missing parameter semantics.

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?

Clearly states it is an internal approval step for quote or booking tools, and enumerates the exact actions to perform (read back email, confirm, set flag, send email). This distinguishes it from other tools by outlining its specific role and workflow.

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?

Provides explicit step-by-step instructions on when and how to use the tool, including prerequisites (read back guestEmail, set emailConfirmedByTraveler after confirmation) and post-conditions (send email, instruct traveler). Also includes a clear directive on what not to mention, which is valuable guidance for the agent.

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

All ATA Travel tools Inspect

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

Need Help?