ATA Travel

suggest_traveler_memory

Save or update one durable traveler memory for personalization. Use only for stable, travel-relevant preferences or constraints explicitly stated by the traveler.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`key`	Yes	Stable normalized memory key. Choose the closest allowed key.
`type`	Yes	Memory category.
`value`	Yes	Small JSON value, e.g. {"hasServiceDog":true} or {"typicalAdults":2,"typicalChildren":1}.
`source`	No		USER_STATED
`summary`	Yes	Short practical note, without speculation or sensitive details.
`confidence`	No	Confidence in this memory. Use 1 for explicit user statements, lower for inferred patterns.
`travelerId`	Yes	Verified traveler ID from the private traveler context.
`visibility`	No		AGENT_ONLY
`travelerAssertion`	No	Current signed ATA traveler assertion matching travelerId; required on shared transports.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 26, 2026

addedInput schema / properties / travelerAssertion

Added value: +{
+  "description": "Current signed ATA traveler assertion matching travelerId; required on shared transports.",
+  "type": "string"
+}

First observedJun 29, 2026

TDQS

A3.7/5.0

Behavior3/5

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

The description adds 'durable' and confirms write/update semantics, which is consistent with readOnlyHint=false and idempotentHint=false. But it does not disclose return behavior, side effects, or the fact that the schema explicitly permits inferred memories, and the 'explicitly stated' restriction is potentially misleading.

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 two short sentences with the core action front-loaded and no redundant phrasing. Every sentence adds essential selection or invocation context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 9 parameters, no output schema, and many sibling tools, the description is minimal but mostly adequate for selecting it. It is incomplete because it does not clarify upsert behavior, expected response, or how to handle the schema's INFERRED source option, leaving an internal inconsistency for the agent to resolve.

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 description coverage is 78%, so the schema already documents most parameters. The description itself adds no per-parameter detail, and its 'explicitly stated by the traveler' guidance may actually conflict with the source and confidence parameters that allow inferred input.

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?

The description clearly states the action ('Save or update') and the resource ('one durable traveler memory for personalization'), which is specific and distinguishable from read-only siblings like get_traveler_memories. It also clarifies the arguably ambiguous tool name 'suggest_traveler_memory' by indicating it is actually a persistence operation.

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?

The phrase 'Use only for stable, travel-relevant preferences or constraints explicitly stated by the traveler' provides a useful eligibility rule. However, it does not mention alternatives such as get_traveler_memories, and it conflicts with the schema's support for source='INFERRED' and confidence guidance for inferred patterns, making the usage boundary inconsistent.

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?