Skip to main content
Glama

Webz.io News Search

News Search by Webz

news_search_by_webz
Read-onlyIdempotent
Semantic news search - use for any news or current-events question.

params:
- query: natural language search query.
- k: articles to return (1-100).
- trust_gte: optional minimum trust (0.0-1.0).
- score_gte: minimum match score on 0-10 scale (default 4.0; set 0 to disable).
- score_lte: optional maximum match score on 0-10 scale.
- days: lookback days (default window: last 7 days).
- allow_all_dates: search the full indexed coverage window instead of days.
- sort_by: best_score (default), similarity, date_desc, date_asc.
- language: filter by language, e.g. english, hebrew, french (case-insensitive).
- country: ISO-2 country codes in UPPERCASE, e.g. US, IL, GB, DE.
- sentiment: positive, negative, or neutral (case-insensitive; omit to skip).
- category: e.g. Politics, Sport, Health (case-insensitive; maps to IPTC labels).
- domain: include only these source domains, e.g. cnn.com, yahoo.com.
- exclude_domain: exclude these source domains (must not overlap with domain).
- topic: News API topic tags (case-insensitive).
- person: named people mentioned in articles (case-insensitive).
- organization: organizations mentioned in articles (case-insensitive).
- location: places mentioned in articles (case-insensitive).
- ticker: stock ticker symbols (case-insensitive; normalized to uppercase).
- source_type: local_news, newsroom, or gov_news (case-insensitive). When the user asks for local news, local outlets, or a local news search, set source_type to ["local_news"] and do not leave that only in the query text. newsroom is for national or general newsrooms. gov_news is for government sources.
- political_bias: political bias label from trust metadata (case-insensitive).
- trust_category: trust category labels (case-insensitive).
- domain_rank_gte: minimum source domain rank (integer).
- domain_rank_lte: maximum source domain rank (integer).
- allow_multiple_chunks_per_article: when true, return multiple chunks from the same article.

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": "news_search_by_webz"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNo
daysNo
queryYes
topicNo
domainNo
personNo
tickerNo
countryNo
sort_byNobest_score
categoryNo
languageNo
locationNo
score_gteNo
score_lteNo
sentimentNo
trust_gteNo
source_typeNo
organizationNo
exclude_domainNo
min_similarityNo
political_biasNo
trust_categoryNo
allow_all_datesNo
domain_rank_gteNo
domain_rank_lteNo
allow_multiple_chunks_per_articleNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, open-world, non-destructive behavior, so the description adds useful operational context beyond safety hints: default lookback of 7 days, default score threshold of 4.0, domain/exclude_domain non-overlap, and source_type routing for local-news queries. It does not describe return structure, but an output schema exists to carry that burden.

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?

The structure is front-loaded with purpose followed by a compact parameter reference. The list is long, but that is proportionate to 26 parameters and nearly every line adds concrete semantics rather than filler.

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?

For a 26-parameter semantic search tool, the description covers defaults, filtering behavior, value formats, and special source-type handling, while the output schema handles return values. Its main completeness gap is the undocumented min_similarity parameter, whose default of 0.4 is invisible unless the agent reads the schema.

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 description coverage is 0%, so the description must carry parameter meaning, and it largely does. It documents scales, defaults, formats, constraint interactions, and accepted values for nearly every parameter, with the notable omission of min_similarity.

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 description opens with a specific verb and resource: 'Semantic news search,' and immediately scopes it to 'any news or current-events question.' An agent can tell exactly what this tool is for without inspecting the schema, and no sibling tools exist to create ambiguity.

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?

It gives clear when-to-use guidance: 'use for any news or current-events question.' There are no alternatives to name because no siblings exist, but it lacks explicit when-not-to-use exclusions or escalation guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.