Skip to main content
Glama

Elegir un vuelo u hotel del viaje

trip_choose

Choose one of the flight or hotel options Wizzo showed in trip_chat, for the trip trip_id: kind is "vuelo" or "hotel", cache_id is the card's cache_id and id the option's id. It saves the choice in the trip (as the web does when the traveller taps «Elegir») and tells Wizzo, who answers with the next step. Only choose what the traveller picked. A choice made by tapping «Elegir» on the card is already saved: do not call trip_choose for it, read Wizzo's answer with trip_chat and the turn_id you were given.

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": {
      "trip_id": "<trip_id>",
      "kind": "<kind>",
      "cache_id": "<cache_id>",
      "id": "<id>"
    },
    "name": "trip_choose"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe id of the chosen option.
kindYes
trip_idYesThe trip id.
cache_idYesThe cache_id of the card the option came from.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and idempotentHint=false; the description supplies the real semantics — the choice is persisted into the trip exactly as the web does, Wizzo is notified, and the reply carries the next step. It also explains the practical consequence of non-idempotency via the card-tap already-saved case. It does not say what happens if a choice is re-made or overridden, or how invalid/expired cache_id is handled.

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 the action and parameter mapping, then the side effect, then the guardrail against double-saving. Every sentence carries information, though the second half is dense and could be split for easier scanning.

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?

For a 4-required-param mutation tool with no output schema, the description covers what it changes, that Wizzo responds with the next step, and the duplicate-save hazard. Remaining gaps are failure modes (stale cache_id, re-choosing a different option) rather than core usage.

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?

With 75% schema coverage the baseline is already 3, and the description goes further: it defines kind as "vuelo" or "hotel" and, crucially, tells the agent that cache_id comes from the card in trip_chat while id identifies the option on that card — provenance the schema does not convey. trip_id itself is only restated.

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?

Names a specific verb ("Choose") and resource (flight or hotel option shown by Wizzo in trip_chat) for a given trip_id, and enumerates the three identifying inputs. It also distinguishes itself from sibling trip_chat by describing the read-vs-write split.

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?

Gives an affirmative rule ("Only choose what the traveller picked") and an explicit exclusion: if the traveller tapped «Elegir» on the card, the choice is already saved, so do not call trip_choose and instead read Wizzo's answer with trip_chat plus the given turn_id. That is a clear when/when-not with the alternative named.

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