Skip to main content
Glama
webdata-tools-mcp

webdata-tools-mcp

Search the web and read the top results as Markdown

search_web_for_rag
Read-onlyIdempotent

Searches the web for AI agents and RAG, opens top results per query, and returns their main content as clean Markdown with title, URL, and word count for prompt context.

Instructions

Web search for AI agents and RAG: runs each query, opens the top results and returns their main content as clean Markdown with title, URL and word count, ready to put in a prompt. Runs the Apify Actor tacps126/rag-web-search on your Apify account (about $0.001 per page; spend per call is capped at $0.5).

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": {
      "queries": "<queries>"
    },
    "name": "search_web_for_rag"
  }
}

Input Schema

NameRequiredDescriptionDefault
countryNoTwo-letter search country.us
queriesYesSearch words or questions, e.g. ["how does retrieval augmented generation work"].
languageNoSearch language code.en
extra_inputNoAdvanced: extra Actor input fields, merged over the defaults.
results_per_queryNoTop results to read per query.

Output Schema

NameRequiredDescriptionDefault
toolYesName of the tool that produced the result.
countYesNumber of records the Actor returned.
itemsYesThe records. Long text fields are shortened to 600 characters.
shownYesNumber of records included in `items` (can be lower than count when the result is long).
truncatedYesTrue when records were left out to keep the result short; ask for fewer items.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.19.0

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, but the description goes well beyond them: it discloses that the call runs the Apify Actor tacps126/rag-web-search on the user's own Apify account, that cost is about $0.001 per page with a $0.5 per-call spend cap, and what each result contains. The account requirement and the spend cap are exactly the operational facts an agent needs before calling a paid, open-world tool.

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

Conciseness5/5

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

Two sentences, both front-loaded with purpose first and cost and mechanics second. Nothing is repeated from the schema or annotations, and every clause (Markdown output shape, Actor name, price, cap) carries information the agent cannot get from structured fields.

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?

With an output schema present and a fully annotated schema, the description supplies the remaining pieces: output format, cost model, account dependency. The one gap is that against a large sibling catalog it gives no routing signal, so an agent must infer from the name alone when this beats a narrower search or single-page reader.

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

Parameters3/5

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

Schema coverage is 100%, so parameter documentation already carries most of the meaning and the baseline of 3 applies. The description does add that every query in the array is run separately and that the top results are what gets read, which clarifies the batch semantics of `queries` and the effect of `results_per_query`, but it says nothing about `country`, `language`, or `extra_input`.

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 names a specific verb ("Web search") and a specific resource ("web"), then adds the second half of the operation: it "opens the top results and returns their main content as clean Markdown with title, URL and word count." That search-plus-read framing distinguishes it from a plain results-only search or a single-URL reader among the siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied through the audience framing "for AI agents and RAG" and "ready to put in a prompt," which tells the agent this output is meant to be pasted into a context window. There is no explicit when-to-use, when-not-to-use, or named alternative for narrower siblings such as the single-page markdown reader or a plain web search.

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