Skip to main content
Glama

web_search

Find ranked, de-duplicated URLs and snippets for a query, then fetch each needed page with read_url before answering.

Instructions

Find URLs to read. Returns a ranked, de-duplicated list (title + URL + snippet), fusion-merged with reciprocal-rank fusion. Keyless by default (DuckDuckGo); also uses SearXNG/Exa/Brave/Tavily when their keys are configured. Snippets are not the page. Call read_url on each URL you need, including when a hit is 403/429, a challenge, or thin. Do not answer from the snippet. Returns a formatted text block that starts with that warning, or an 'Error: ...' string when every provider fails. Update check: when a newer release exists, a successful result also carries 'update_available' plus, at most once per 24 hours, one line telling the agent. The check is one GET to the GitHub latest release of capad-xyz/searchts, at most once per 24 hours, cached in ~/.searchts/update-check.json, with a searchts User-Agent and nothing about the user. Nothing is installed or changed. SEARCHTS_NO_UPDATE_CHECK=1 turns the check and the note off.

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": "web_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes
max_resultsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.8.0
    • addedInput schema / properties / max_results / default
      Added value: +5
    • removedInput schema / properties / max_results / description
      Removed value: -"How many results to return (default 5; clamped to 1-25)."
    • addedInput schema / properties / max_results / title
      Added value: +"Max Results"
    • removedInput schema / properties / query / description
      Removed value: -"The search query."
    • addedInput schema / properties / query / title
      Added value: +"Query"
    • addedInput schema / title
      Added value: +"web_search_toolArguments"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "result": {
      +      "title": "Result",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "result"
      +  ],
      +  "title": "web_search_toolOutput",
      +  "type": "object"
      +}
  2. First observedv0.5.1

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: keyless DuckDuckGo default with SearXNG/Exa/Brave/Tavily fallback when keys exist, ranked/de-duplicated fusion output, an 'Error: ...' string when all providers fail, and an explicit outbound network disclosure (single GET to GitHub, 24h cache, UA, opt-out env var) with 'Nothing is installed or changed.' That effectively establishes read-only behavior without annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical routing guidance is front-loaded correctly, but roughly a third of the text is an update-check digression that repeats 'at most once per 24 hours' twice and details a cache path and User-Agent the agent does not need to select or call the tool. Useful disclosure, but disproportionate to the tool's core job.

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?

An output schema exists, so return values are already covered, yet the description still explains the return shape and the leading warning line. Behavioral context is thorough for a multi-provider search; the only real gap is the absence of anything about max_results, which matters for cost and result volume.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across both parameters, so the description must compensate and does not. 'query' is inferable from 'Find URLs', but max_results (default 5) is never mentioned — no upper bound, cost implication, or guidance on when to raise 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?

Opens with a specific verb+resource — 'Find URLs to read' — naming the resource it produces (URLs) rather than a page. This cleanly separates it from siblings like read_url, grab_site, and fetch_asset that consume URLs instead of producing them.

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?

Explicitly routes the agent to the alternative: 'Call read_url on each URL you need, including when a hit is 403/429, a challenge, or thin. Do not answer from the snippet.' It also states the when-not condition (snippets are not the page). This is textbook when/when-not/alternative guidance.

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