Skip to main content
Glama

travel

by ai.autonomad
OverviewDiscussionsAdmin

message_autonomad

Destructive

Sends the signed-in person's question or problem to Autonomad and returns the answer in the same call. reply is the answer from Autonomad's automated responder, which can use the person's own flight, hotel and experience details; it is saved in their Autonomad thread. If it cannot be answered automatically, or needs_person is true, a support ticket is opened instead and what_happens_next states what is pending; repeat that without adding a reply time or a promise that a person will respond. A tool error means the message was not answered. This tool does not change bookings: to cancel, rebook or change one, use preview_booking_change first. Do not include card numbers, passwords or one-time codes.

Input Schema

NameRequiredDescriptionDefault
textYesThe question or problem, in the person's words where possible. Up to 4000 characters.
needs_personNotrue only when the person asks for a human, or the instant answer did not solve it: opens a support ticket instead of answering automatically.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / action
      Removed value: -{
-  "description": "Optional, and only with Trip Concierge on the trip: a cancellation, or a rebook/modify request for the concierge.",
-  "properties": {
-    "component_ids": {
-      "description": "cancel: only these parts (from the preview). Omit for all.",
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    "confirm": {
-      "description": "false/omitted = preview only, nothing changes or is passed on; true = cancel, or pass the rebook/modify to the concierge, only after the person agreed.",
-      "type": "boolean"
-    },
-    "reference": {
-      "description": "The booking reference the person was given (e.g. ANM-1A2B3C4D), or the trip id.",
-      "type": "string"
-    },
-    "type": {
-      "enum": [
-        "cancel",
-        "rebook",
-        "modify"
-      ],
-      "type": "string"
-    }
-  },
-  "required": [
-    "type",
-    "reference"
-  ],
-  "type": "object"
-}
    • changedInput schema / properties / text / description
      Previous value: -"The question, problem or requested change, in the person's words where possible. Up to 4000 characters."New value: +"The question or problem, in the person's words where possible. Up to 4000 characters."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that the reply is persisted in the person's Autonomad thread, that a support ticket is opened when automatic answering fails, that `what_happens_next` carries the pending state, and that a tool error means the message was not answered. It also clarifies the mutation scope (no booking changes) despite destructiveHint=true, resolving ambiguity the annotations leave open.

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?

Front-loaded with purpose, then fallback behavior, then the sibling redirect and the sensitive-data warning — every sentence is load-bearing. It is dense and slightly run-on in the ticket-handling clause, but nothing is redundant.

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?

With no output schema, the description still names the returned fields (`reply`, `what_happens_next`) and their semantics, and it closes the safety gap for a destructive/open-world write by prohibiting card numbers, passwords and one-time codes. Nothing an agent needs to invoke it correctly is missing.

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 baseline is 3, but the description adds real meaning: `needs_person` is tied to the concrete consequence of opening a ticket instead of answering, and the reply/`what_happens_next` outputs are explained. It stops short of adding guidance on formulating `text` beyond the schema's own note.

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 (sends) and resource (the person's question to Autonomad) plus the round-trip behavior (returns the answer in the same call). It also draws the boundary against sibling tools by name, telling the agent this does not change bookings and that preview_booking_change is the route for that.

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?

Explicit when-to-use (questions/problems from the signed-in person), when-not-to-use (cancelling, rebooking, changing a booking), and the alternative to use instead. It even prescribes handling of the fallback path (needs_person / ticket opened) and forbids adding a response-time promise.

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

All travel 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