Himalayan Lighthouse

Search the network

search

Read-onlyIdempotent

Search one network of free websites (courses on any subject, a multilingual dictionary and encyclopedia, live disaster warnings, visa rules, everyday tools) for the pages that answer a query. Returns up to 8 results, each with an id to pass to fetch, a title and an address a person can open. Use it when the user asks about a subject one of these sites covers; it does not search the wider web.

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": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	The subject, in a few words.

Output Schema

Name	Required	Description	Default
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 10, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile needs no restating. The description adds behavior beyond them: a hard cap of 8 results, per-result fields (id, title, address), and the intended id-to-`fetch` workflow. It does not discuss ranking or what happens when nothing matches, but that is largely covered by the output schema.

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?

Two sentences, front-loaded with what is searched and where, then the result shape and the usage trigger. No filler and nothing repeated from structured fields except the minimal result shape needed to explain the handoff to `fetch`.

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 one-parameter read tool with full annotation coverage and an output schema, this covers everything an agent needs: scope, exclusions, result cap, and the follow-up tool. Nothing material is left to inference.

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% for the single parameter, so the baseline is already satisfied. The description adds framing the schema lacks: the query is a subject matched against a fixed domain set rather than arbitrary web text, which shapes how an agent should phrase it.

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?

Specific verb (search) plus a precisely bounded resource (one network of free websites, with the content domains enumerated) and an explicit negative scope: 'it does not search the wider web.' An agent can distinguish this from `fetch` and from any general web search without opening the schema.

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 a concrete trigger ('when the user asks about a subject one of these sites covers') and an explicit exclusion (no wider web). It also explains the follow-on step by noting the returned id is passed to `fetch`, though it does not address when to prefer `suggest` or `list_sites` over searching directly.

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

All Himalayan Lighthouse 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?