[skiplagged] Search Skiplagged support articles for answers about its services, products, and policies.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Concise FAQ question for retrieval. Do not include personal identifiers, account IDs, or session details. | |
| top_k | No | Number of top FAQ sources to return (1-5) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'search support articles', which implies a read operation, but does not disclose any further traits such as return format, pagination, rate limits, or whether results are article snippets or full text. This absence of behavioral context is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the domain tag and directly states the tool's purpose. Every word earns its place, with no unnecessary filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a relatively simple tool with two documented parameters and no output schema, the description gives the minimum viable context. However, it lacks detail on what results look like and does not guide query formulation beyond what the schema already says. This leaves some ambiguity for an agent unfamiliar with the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers both parameters with descriptions: `query` for the FAQ question and `top_k` for the number of sources. With 100% schema coverage, the description adds no additional parameter-level meaning, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches Skiplagged support articles for answers related to services, products, and policies. This specific verb+resource combination distinguishes it from sibling tools focused on flights, hotels, or destinations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear context: use this tool for FAQ-style questions about Skiplagged services, products, or policies. It implies when to use it (when user asks about support topics) but does not explicitly state when not to use it or name alternatives. This is strong contextual guidance without exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are namespaced by vendor and resource, so ferry, tour, flight, hotel, and experience searches are broadly distinguishable. However, hotel search exists in both skiplagged and trivago, ferryhopper_search_trips is a deprecated duplicate of search_trips_v2, and several skiplagged calendar/anywhere tools overlap in flight-price discovery, which can cause misselection.
Naming conventions are mixed across the set: plain underscores (airports_search), vendor-prefixed underscores (ferryhopper_get_ports), redundant prefixes (skiplagged_sk_hotels_search, trivago_trivago-accommodation-search), and hyphenated sub-APIs (tourradar_b2b-tour-details, tourradar_vertex-tour-search). There is no consistent verb_noun pattern and at least one version-suffixed deprecated name.
With 56 tools, the server falls into the extreme-mismatch count band. The breadth is partly explained by eight vendor integrations, but many lookups, near-duplicate searches, and deprecated tools could be consolidated or split into focused MCP servers.
The tool surface covers most of the travel-planning lifecycle: airports, airlines, visa rules, FCDO advice, flights, hotels, cars, ferries, experiences, and tours including search, details, and tour booking. The main gaps are that only tours have an actual booking flow and there is no update/cancel or post-booking management.