TripWorks Tour and Activity Booking

Discover what you can do

discover

Read-only

Find out what this connection can do and how to call it. With no arguments it returns the operations grouped by entity, with read and write counts and operation names only. Entities include booking, trip, trip_note, knowledge_base, customer, experience, customer_type, location, reseller, restriction, promo_code, review, phone_call, audit_log, user_avatar, report, manifest, analytics and search. Pass search (best matches first, default 5, at most 25) or entity (all of that entity's operations). Each operation comes back with its kind, description and arguments (type, required, meaning), which is everything needed to call it with query (reads) or execute (writes). List operations also take limit and cursor.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "discover"
  }
}

Input Schema

Name	Required	Description
`kind`	No	read keeps only operations for query, write keeps only operations for execute. Omit for both.
`limit`	No	With search: how many ranked matches to return. Default 5, at most 25.
`entity`	No	An entity from the no-argument overview, for example booking or customer. Lists all of that entity's operations; combined with search it restricts the ranking to that entity.
`search`	No	Words to look for in operation names, titles and descriptions, for example booking waiver or revenue by month. Returns the best matches first, up to limit.

Output Schema

Name	Required	Description	Default
`entities`	No
`operations`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds real value beyond them: the no-argument response shape (grouped by entity, read/write counts, names only), ranked-match ordering, and the 5-default/25-max ceiling. It also discloses that returned operations include kind, description and arguments, which is precisely the call-readiness contract an agent needs. Minor gap: 'List operations also take limit and cursor' references a cursor parameter that does not exist in the schema.

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 behavior, then parameters — a sensible order with no filler sentences. The middle sentence enumerating nineteen entity names is the only bloat, though it does help an agent guess valid values for the entity parameter.

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?

For a four-parameter, zero-required discovery tool with an output schema, the description covers invocation modes, return shape and result limits. The output schema carries the response structure, so nothing essential is missing; the cursor mention is a small inconsistency rather than a completeness gap.

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 the schema already documents kind, limit, entity and search in detail; baseline 3 applies. The description reinforces limit's default and cap and explains the search+entity interaction, but never mentions the 'kind' filter at all, so it adds little beyond the schema for that parameter.

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 ('Find out what this connection can do and how to call it') and immediately clarifies the scope: a discovery/meta tool that returns operations grouped by entity. The closing sentence routes the agent to the actual invocation siblings ('call it with query (reads) or execute (writes)'), so it is clearly distinguishable from both.

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

Usage Guidelines4/5

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

Gives explicit usage modes: no arguments for the full overview, 'search' for ranked matches, 'entity' for all of one entity's operations, and notes that combining them restricts ranking. It also implicitly names alternatives by saying results are what you need to call query/execute. It stops short of stating when NOT to use this tool (e.g. once you already know the operation name).

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

All TripWorks Tour and Activity Booking 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.