olostep-mcp

Search Web

search_web

Read-onlyIdempotent

Find web pages on a topic when no URL is known: returns URLs, titles, and descriptions, and can optionally scrape each result's content as markdown.

Instructions

Use this when you need web pages on a topic and do not have a URL yet. Returns up to limit results (1-25), each with its URL, title and description. Set scrape_results to true to also get each result page's content as markdown in the same call (each scraped page costs extra credits); otherwise pass the URLs you need to scrape_website, or to batch_scrape_urls for many. Use include_domains to search one site. For a direct factual answer with sources, use answers.

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": "search_web"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Number of results to return, from 1 to 25. Default: 10.
`query`	Yes	Search query in natural language.
`max_characters`	No	With scrape_results, the maximum characters of content returned per page. Default: 20000.
`scrape_results`	No	Also scrape each result and return its content as markdown. Each scraped page uses extra credits.
`exclude_domains`	No	Never return results from these domains.
`include_domains`	No	Only return results from these domains, e.g. ["docs.olostep.com"].

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv1.0.21Nov 13, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedInput schema / properties / country

Removed value: -{
-  "default": "US",
-  "description": "Optional country code for localized results (e.g., US, GB).",
-  "type": "string"
-}

addedInput schema / properties / exclude_domains

Added value: +{
+  "description": "Never return results from these domains.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / include_domains

Added value: +{
+  "description": "Only return results from these domains, e.g. [\"docs.olostep.com\"].",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / limit

Added value: +{
+  "default": 10,
+  "description": "Number of results to return, from 1 to 25. Default: 10.",
+  "maximum": 25,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / max_characters

Added value: +{
+  "default": 20000,
+  "description": "With scrape_results, the maximum characters of content returned per page. Default: 20000.",
+  "minimum": 1,
+  "type": "integer"
+}

changedInput schema / properties / query / description

Previous value: -"Search query"New value: +"Search query in natural language."

addedInput schema / properties / scrape_results

Added value: +{
+  "default": false,
+  "description": "Also scrape each result and return its content as markdown. Each scraped page uses extra credits.",
+  "type": "boolean"
+}

Addedv1.0.0Jan 3, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description adds genuinely useful behavior: scraping inside the call costs extra credits per page, and each result carries URL, title and description. It doesn't discuss rate limits or result ordering, which keeps it short of a 5.

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?

Front-loaded with the usage condition, then return shape, then the expensive option, then routing to siblings. Every clause carries a decision-relevant fact; nothing is padding.

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 still explains the return shape (URL, title, description, plus markdown when scraping) and the cost implication of the expensive path. For a 6-parameter read tool, that is enough for an agent to call it correctly.

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: `scrape_results` triggers extra credit spend and in-call content return, and `include_domains` is framed as restricting to one site. The `limit` range is only repeated from the schema, so it isn't a full override.

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 ("web pages on a topic") plus the scope condition (no URL yet), and names `answers` as the different route for direct answers. An agent can distinguish it from `scrape_website`/`batch_scrape_urls` without opening any schema.

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?

Gives explicit when-to-use ("when you need web pages on a topic and do not have a URL yet"), when-not (use `answers` for a direct factual answer with sources), and named alternatives with the conditions that select them (`scrape_website` for a few URLs, `batch_scrape_urls` for many).

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

Deploy Server