Skip to main content
Glama
Sign In

Webz.io Blogs

by io.webz
OverviewDiscussionsAdmin

Search Webz Blogs

search_webz_blogs
Read-onlyIdempotent

Search blog posts only (GET /api/blogs).

A named site list is a q clause: custom_sites_list:ID. Example: custom_sites_list:SB_c41211dd. The field name is custom_sites_list. The list identifier is preserved exactly as supplied.

Blogs do not have news category, topic, sentiment, or trust filters. They do have people, organizations, and locations.

Boolean query syntax is shared by news, blogs and forums. Unfielded terms match the post title, body and thread title. Spaces mean AND; AND, OR and NOT are uppercase. A leading minus means NOT. Parentheses group terms: (solar OR wind) storage. Quotes match exact phrases: "climate change". Proximity syntax "apple watch"~3 matches within 3 words, with at most 10 proximity operators. Prefix wildcards are supported (crypt*); leading wildcards are stripped. The $ suffix disables stemming (gold$) for English, Spanish, Arabic, Russian and French. Unbalanced quotes or parentheses return HTTP 400. Filters are field:value clauses within q. Values are case-insensitive; values with spaces are quoted. Unknown filter values can produce zero hits. Zero hits are a successful empty result, not an API error. Numeric and time filters support > and <, for example domain_rank:<1000 and published:>UNIX_MILLISECONDS. A language filter selects a language analyzer. Supported lowercase language names: afrikaans, albanian, amharic, arabic, armenian, azerbaijani, basque, belarusian, bengali, bulgarian, burmese, catalan, cherokee, chinese, chineset, croatian, czech, danish, dhivehi, dutch, english, estonian, finnish, french, galician, georgian, german, greek, gujarati, hebrew, hindi, hungarian, icelandic, indonesian, inuktitut, irish, italian, japanese, kannada, khmer, korean, kurdish, laothian, latvian, lithuanian, macedonian, malay, malayalam, maltese, norwegian, oriya, persian, polish, portuguese, punjabi, romanian, russian, serbian, sinhalese, slovak, slovenian, spanish, swahili, swedish, syriac, tagalog, tamil, telugu, thai, tibetan, turkish, ukrainian, urdu, vietnamese, welsh, yiddish.

Source filters inside q: site:cnn.com (domain), site_full:forums.example.com (exact host), site_suffix:co.uk, site_section:business, site_title:"morning post", section_title:sports, country:US (ISO-2; GB represents the United Kingdom), domain_rank:<1000 (1-1000000, lower is more popular), and site_category:tech (snake_case). Examples of site categories include tech, financial_news, world_soccer, travel, politics, health, music and real_estate. custom_sites_list:hot_sites matches the named site list using its supplied identifier.

Content filters, inside q: title:bitcoin, text:"supply chain", author:"jane doe", published:>UNIX_MS, crawled:>UNIX_MS, external_links:github.com.

Blog entity filters, inside q:

  • person:"elon musk", organization:nvidia, location:paris

  • person.positive, person.negative, person.neutral, and the same three suffixes for organization and location

  • ticker:AAPL, exchange:NASDAQ (also NYSE, LON) Entities are extracted for English, German, Spanish, and Italian. category:, sentiment: and trust.* are unsupported on blogs and produce zero hits.

Examples:

  • site:medium.com "supply chain" language:english

  • author:"jane doe" title:bitcoin language:english

  • organization:nvidia language:english

Separate tool arguments: size is 1-100, default 10; the API default is 100. Responses report total_results (match count) and more_results_available (unread matches). sort defaults to crawled; order defaults to asc for crawled, updated and domain_rank, and desc otherwise. crawled supports full-result pagination. days defaults to the last 3 days. ts is a Unix millisecond timestamp that overrides days and also serves as a pagination cursor. News history beyond 31 days requires allow_news_history=true and extra credits. highlight=true marks matched words in excerpts. include_syndicated=true includes syndicated copies (default false). webz_reporter=true includes Webz Reporter posts (default false); this is a separate argument, not a q filter. warning defaults to true. Subsequent pages use the returned ts, ni, ns and from_offset; ni and ns are opaque values. from_offset applies to non-crawled sorts.

The server rate limit is 3 requests per second per token and endpoint. total_results=0 with an empty posts array is a successful search with no matching content.

Reference documentation: Filters: https://docs.webz.io/docs/webz/blogs-api-filters Query syntax: https://docs.webz.io/docs/webz/news-blogs-forums-query-syntax Parameters: https://docs.webz.io/docs/webz/news-blogs-forums-parameters Product: https://docs.webz.io/docs/webz/blogs

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": {
      "q": "<q>"
    },
    "name": "search_webz_blogs"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesBoolean query with field:value filters. A space means AND; AND, OR and NOT are uppercase. A leading minus also means NOT (tesla -car). Quoted phrases and filter values may contain spaces, for example author:"jane doe". Examples: language:english site:cnn.com country:US. Language values are lowercase full names (hebrew); country values are ISO-2 (GB). Numeric comparisons use > or <, for example domain_rank:<1000. size, sort and days are separate tool arguments.
niNoOpaque next-page cursor returned by the preceding response.
nsNoOpaque next-page cursor returned by the preceding response.
tsNoWindow start or returned pagination timestamp in Unix milliseconds. Overrides days. Pagination uses the value returned in the preceding response.
daysNoLookback in days. The API default is 3; 7 is one week and 31 is the standard history limit. Ignored when ts is provided. Earlier news history requires allow_news_history=true and extra credits.
sizeNoPosts per page, 1-100; the tool default is 10 and the underlying API default is 100. total_results is the total match count. Returned cursors identify subsequent pages.
sortNoSort field. Default crawled supports pagination through the full result set and history. crawled, updated and domain_rank default to asc; other fields default to desc. Other values: relevancy, published, thread.published, performance_score, replies_count, participants_count, ord_in_thread, rating, social.facebook.likes, social.facebook.shares, social.facebook.comments, social.gplus.shares, social.pinterest.shares, social.linkedin.shares, social.stumbledupon.shares and social.vk.shares. Engagement and social sorts apply to news.crawled
orderNoasc or desc. When omitted, the API defaults to asc for crawled, updated and domain_rank, and desc for other sorts.
warningNoWhen true (default), the API returns query warnings without failing the search.
highlightNoWhen true, excerpts highlight the matched terms.
from_offsetNoReturned pagination offset for non-crawled sorts.
webz_reporterNoWhen true, include Webz Reporter posts. Default false. This is its own argument. webz_reporter:true inside q does not include those posts.
allow_news_historyNoEnables news history beyond 31 days with additional credit costs. News only.
include_syndicatedNoWhen true, include syndicated copies. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already mark the tool as read-only, open-world, idempotent, and non-destructive, but the description adds substantial operational context beyond them: a 3-request-per-second rate limit, HTTP 400 on unbalanced quotes or parentheses, zero hits as a successful empty result, extra credits for news history, and pagination cursor behavior. These details materially help an agent predict behavior and handle responses.

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 description is front-loaded and well-organized with paragraphs, bullets, and examples, but it is extremely long for a tool definition, including a full language list and repeated details such as zero-hit success and size defaults. The information is useful, but the length and repetition reduce conciseness.

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 complex 14-parameter search tool with no output schema, the description is complete enough to call correctly: it covers query syntax, filters, defaults, pagination, rate limits, error behavior, and key response fields like total_results and more_results_available. Nothing critical about invocation or interpreting empty results appears to be missing.

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 schema already documents the 14 parameters, but the description adds meaningful query semantics for 'q', including field filters, entity filters, Boolean syntax, proximity syntax, wildcard rules, language values, and examples. It also clarifies defaults and pagination differences for size, sort, days, ts, from_offset, ni, and ns, though much of that overlaps with the schema descriptions.

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?

The opening sentence states a specific verb, resource, and endpoint: 'Search blog posts only (GET /api/blogs).' It also clarifies the tool's boundaries by distinguishing blog filters from news filters, so an agent can tell what this tool is for 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?

The description gives clear usage context through supported and unsupported filters, examples such as 'site:medium.com "supply chain" language:english', and explicit statements that category, sentiment, and trust filters are unsupported on blogs. It does not name alternative tools because no siblings are provided, but it also does not explicitly frame when to prefer blogs over news or forums beyond the 'blogs only' scope.

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

All Webz.io Blogs toolsInspect
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