Skip to main content
Glama
octen-mcp

octen-mcp

Official
by Octen-Team

Broad Search

broad_search
Read-only

Expands multi-part research questions into several sub-queries and runs them concurrently across the web to cover comparisons, surveys, and multi-angle topics in one call.

Instructions

Search the web across many angles in one call — for comparisons, research, surveys, and questions with several distinct parts. Expands your question into multiple sub-queries and runs them concurrently.

USE WHEN the question has multiple distinct parts or entities that one search cannot cover:

  • comparing vendors / products / pricing across many sources

  • literature reviews, market or landscape surveys

  • open-ended "what are the options for X" / "how do people solve Y"

  • a question that clearly decomposes into 3+ independent sub-questions

  • multi-angle questions about recent events ("what shipped across the industry this month") — do NOT loop news_search

DO NOT USE for anything another tool answers directly — fanning out costs Nx and returns pages where those return the answer:

  • a single fact, entity, or document → use search

  • a company or the people in one, including its financials → use business_search

  • news or recent events on a single topic → use news_search (multi-angle is the exception above)

  • a real-world place, address, opening hours → use place_search

  • the URL of a site or docs page you could almost name → use pulse_search

  • images or videos → use image_search / video_search

  • re-running a disappointing search → do NOT call broad_search twice; follow up with a targeted search or extract on the specific gaps

  • reading a page you already have the URL for → use extract

  • a straight A-vs-B comparison of two known entities → two targeted search calls are cheaper and more controllable

COST: fans out into max_queries concurrent searches — roughly Nx the cost and notably higher latency than a single search. When in doubt, prefer search.

QUERY: pass one natural-language question (max 500 chars). Resolve pronouns and references from the conversation first — "how does it compare to the other one" is a useless query. Do NOT pre-split into sub-queries; that is this tool's job. For broader coverage raise max_queries rather than calling repeatedly. Per-sub-query options (count, language filter, domain / text filters, time window, highlight / full_content, media) match search and apply to every sub-query.

RESULTS are grouped per sub-query and NOT deduplicated — the same URL may appear under several sub-queries.

max_queries: 3-5 focused comparison (2-3 entities) | 5-10 multi-facet research | 10-20 landscape scan | 20-30 exhaustive survey

For a single focused lookup use search; to read a specific page use extract. Reach for this one only when no single tool above covers the question.

keywords: web search, search the web, look up, find information, research, compare, comparison, versus, alternatives, options, landscape, survey, market research, pricing, latest, current information, multi-part question

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": "broad_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNoNumber of results to return (1-100). Default 5.
queryYesNon-empty search query. Max 500 chars.
formatNoFormat of returned content. Default text.text
timeoutNoRequest timeout in seconds (1-300). Defaults to 120s if unset. Raise it for large `max_queries` surveys, which legitimately take longer.
end_timeNoUpper bound for the time window, ISO 8601.
languageNoLanguages to filter results by, as ISO 639-1 codes. Empty = no filter.
highlightNoReturn a ranked highlighted snippet per result. Omit to use the server default.
safesearchNoAdult-content filter. Default strict.strict
start_timeNoLower bound for the time window, ISO 8601 (e.g. '2025-01-01T00:00:00Z').
time_basisNoWhich timestamp the time window filters against: page `published` date, last `crawled` date, or `auto`. Default auto.auto
time_rangeNoRelative time window (e.g. `week`, `month`). Mutually exclusive with `start_time`/`end_time` — if both are given, the absolute range wins.
max_queriesNoUpper bound on the number of sub-queries generated (1-30). Default 5 — raise toward 30 for surveys / deeper research, lower for a tighter search.
exclude_textNoDrop results whose content contains any of these strings. Max 5, each ≤30 chars.
full_contentNoReturn the cleaned full page body per result. Heavier than `highlight` — use only when the snippet isn't enough. Omit to use the server default (off).
include_textNoOnly return results whose content contains all of these strings. Max 5, each ≤30 chars.
include_imagesNoReturn image URLs (and a cover image) found on each result page.
exclude_domainsNoDrop results from these domains. Max 1200, each ≤60 chars.
include_domainsNoOnly return results from these domains (e.g. 'arxiv.org'). Max 1200, each ≤60 chars.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.1
    • removedInput schema / properties / topic
      Removed value: -{
      -  "default": "general",
      -  "description": "Search category: `general` for broad web search, `news` for news-focused results. Default general.",
      -  "enum": [
      -    "general",
      -    "news"
      -  ],
      -  "type": "string"
      -}
  2. Changed2 schema fields changedv0.5.2
    • changedInput schema / properties / query / description
      Previous value: -"Search query. Max 500 chars."New value: +"Non-empty search query. Max 500 chars."
    • addedInput schema / properties / query / minLength
      Added value: +1
  3. Changed7 schema fields changedv0.5.0
    • changedInput schema / properties / exclude_domains / description
      Previous value: -"Drop results from these domains. Max 150, each ≤30 chars."New value: +"Drop results from these domains. Max 1200, each ≤60 chars."
    • changedInput schema / properties / exclude_domains / items / maxLength
      Previous value: -30New value: +60
    • changedInput schema / properties / exclude_domains / maxItems
      Previous value: -150New value: +1200
    • changedInput schema / properties / include_domains / description
      Previous value: -"Only return results from these domains (e.g. 'arxiv.org'). Max 1000, each ≤30 chars."New value: +"Only return results from these domains (e.g. 'arxiv.org'). Max 1200, each ≤60 chars."
    • changedInput schema / properties / include_domains / items / maxLength
      Previous value: -30New value: +60
    • changedInput schema / properties / include_domains / maxItems
      Previous value: -1000New value: +1200
    • removedInput schema / properties / include_videos
      Removed value: -{
      -  "default": false,
      -  "description": "Return video URLs found on each result page.",
      -  "type": "boolean"
      -}
  4. Changed2 schema fields changedv0.4.2
    • changedInput schema / properties / timeout / description
      Previous value: -"Request timeout in seconds (1-60)."New value: +"Request timeout in seconds (1-300). Defaults to 120s if unset. Raise it for large `max_queries` surveys, which legitimately take longer."
    • changedInput schema / properties / timeout / maximum
      Previous value: -60New value: +300
  5. Changed1 schema field changedv0.3.5
    • addedInput schema / properties / language
      Added value: +{
      +  "default": [],
      +  "description": "Languages to filter results by, as ISO 639-1 codes. Empty = no filter.",
      +  "items": {
      +    "enum": [
      +      "ar",
      +      "de",
      +      "en",
      +      "es",
      +      "fr",
      +      "hi",
      +      "id",
      +      "it",
      +      "ja",
      +      "ko",
      +      "nl",
      +      "pl",
      +      "pt",
      +      "ru",
      +      "th",
      +      "tr",
      +      "vi",
      +      "zh"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  6. Changed1 schema field changedv0.3.4
    • removedInput schema / properties / country
      Removed value: -{
      -  "default": "auto",
      -  "description": "Follow ISO 3166, the International Standard for country codes and codes for their subdivisions (e.g. `US`, `JP`); `auto` (default) determines it automatically.",
      -  "type": "string"
      -}
  7. Changed1 schema field changedv0.3.3
    • addedInput schema / properties / country
      Added value: +{
      +  "default": "auto",
      +  "description": "Follow ISO 3166, the International Standard for country codes and codes for their subdivisions (e.g. `US`, `JP`); `auto` (default) determines it automatically.",
      +  "type": "string"
      +}
  8. Addedv0.3.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnly/openWorld/non-destructive; the description adds substantial context beyond that: the Nx cost and higher latency of fan-out, a 'when in doubt prefer search' heuristic, the non-deduplicated per-sub-query result grouping, and timeout guidance for large surveys. It also forbids a specific failure pattern (re-running a disappointing search).

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 clearly sectioned USE WHEN / DO NOT USE / COST / QUERY / RESULTS, so an agent can scan it fast. It is long, and the closing line ("For a single focused lookup use `search`; to read a specific page use `extract`") restates guidance already given above — mild redundancy, but the overall length is justified by the tool's complexity.

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 an 18-parameter tool with nested objects and no output schema, the description covers everything an agent needs: cost model, query formulation, sub-query count sizing, result grouping shape, and tool routing. Nothing critical 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%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains how to phrase `query` (one natural-language question, resolve pronouns, do not pre-split), gives sizing bands for `max_queries` (3-5 for 2-3 entity comparisons through 20-30 for exhaustive surveys), and notes that all per-sub-query options apply to every sub-query — a non-obvious semantic the schema cannot express.

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 ("Search the web across many angles in one call") plus the mechanism (expands into sub-queries run concurrently). It explicitly distinguishes itself from every sibling by naming them (search, news_search, business_search, place_search, pulse_search, image_search, video_search, extract).

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?

Unusually explicit: a USE WHEN list with concrete scenarios (vendor comparison, literature review, 3+ independent sub-questions) and a DO NOT USE list routing each alternative case to its correct sibling tool. It even resolves the tricky edge cases — multi-angle news goes here while single-topic news goes to news_search, and A-vs-B of two known entities should be two search calls.

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