Webz.io Forums segmentation

Aggregate Webz Forums

aggregate_webz_forums

Read-onlyIdempotent

Count forum posts instead of returning them (GET /seg_api/forums).

Aggregates forum posts by forum, board, author and other supported fields. Example: which forums and boards talk about bitcoin this week.

This is forums and discussions only. It returns buckets with counts, not posts. Each underlying field request costs 1 credit. A response has at most 10 buckets. Returned from_offset values paginate through up to 100 buckets.

q is the same boolean language as search. A space means AND. days is the crawl lookback. Named site lists are q clauses, for example custom_sites_list:hot_sites. Default 7 is the past week. The maximum is 31.

field is the bucket. Default is thread.site,thread.site_section, as two requests. Allowed fields: thread.site, thread.site_suffix, thread.site_full, thread.site_section, thread.site_type, thread.country, thread.url, author, language, site_category, published, rating. Forums have no person, company, location, or ticker extraction, so those fields are rejected here. topic, sentiment, category, and trust.* exist on news only.

Separate segmentation arguments: 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. from_offset paginates beyond the first 10 buckets.

Examples:

q=bitcoin days=7
q=bitcoin field=author days=7
q="product recall" field=thread.country language:english days=7

Reference documentation: Segmentation: https://docs.webz.io/docs/webz/news-blogs-forums-segmentation

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": "aggregate_webz_forums"
  }
}

Input Schema

Name	Required	Description	Default
`q`	Yes	Boolean 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.
`days`	No	Lookback in days. Default 7 is the past week. Maximum 31.
`field`	No	Buckets to count. thread.site is the forum, thread.site_section is the board. Default thread.site,thread.site_section runs both. Comma separated.	thread.site,thread.site_section
`from_offset`	No	Returned pagination offset for non-crawled sorts.
`webz_reporter`	No	When true, include Webz Reporter posts. Default false. This is its own argument. webz_reporter:true inside q does not include those posts.
`include_syndicated`	No	When true, include syndicated copies. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds cost ('Each underlying field request costs 1 credit'), response caps ('at most 10 buckets', 'up to 100 buckets' via from_offset), and default segmentation behavior. These are operational traits an agent cannot infer from the annotations or schema.

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 the core distinction and organized into short scannable paragraphs plus concrete examples. There is minor redundancy: the default field value and its 'two requests' cost is stated twice, and 'forums and discussions only' overlaps with 'returns buckets with counts, not posts'.

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?

With no output schema, the description carries the return shape and does so ('buckets with counts, not posts', 10 per response, 100 via offset). Credit cost, pagination, field restrictions, and the separate segmentation flags are all covered, leaving nothing an agent needs to call it correctly.

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

Parameters5/5

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

Schema coverage is 100%, so baseline is 3, but the description meaningfully exceeds it: it enumerates the full allowed field list for the bucket argument, which the schema does not, explains that q uses the same boolean language as search with space-as-AND, states days is the crawl lookback with max 31, and clarifies from_offset paginates beyond the first 10 buckets.

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 and resource ('Count forum posts instead of returning them') plus the underlying endpoint, and immediately contrasts with the retrieval behavior it is not ('It returns buckets with counts, not posts'). The scope boundary ('This is forums and discussions only') and the example use case ('which forums and boards talk about bitcoin this week') make the tool unmistakable.

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 frames when to use it (aggregate rather than retrieve) and when not to: fields like person, company, location, ticker are 'rejected here', and topic/sentiment/category/trust.* 'exist on news only'. It also warns that webz_reporter is 'a separate argument, not a q filter', which prevents a very plausible misuse.

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

All Webz.io Forums segmentation 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.