Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
Scored across 4 tools
Search, research, fetch, and extract each have a distinct primary role, and the descriptions explicitly call out when to use one over another. The only mild ambiguity is between fetch and extract, since both operate on URLs and return page-derived content, but their different outputs (full markdown vs. AI-extracted structured data) are clearly explained.
All four tool names are single lowercase verbs that match their function directly: search, research, fetch, and extract. The pattern is completely consistent and predictable, with no mixed conventions or vague filler names.
Four tools is a well-scoped size for a web research server. Each tool covers a distinct operation—discovery, deep synthesis, targeted fetching, and structured extraction—so none feels redundant or missing.
The tool set covers the full research lifecycle: search for sources, fetch specific URLs, extract structured data from a page, and synthesize an overall report. It includes useful parameters like freshness, domain filtering, and raw HTML access, leaving no obvious dead ends for typical web research workflows.
Fetch a webpage and extract specific information using AI. Use this when you need structured data from a page (e.g. pricing, specs, contact info) rather than the raw content. Costs 10 credits.
If the page has no usable text (empty or JavaScript-rendered body), the model is NOT called: content comes back empty and usage.low_content is true, rather than a fabricated answer. Gate on usage.low_content (or usage.content_chars) to detect pages you cannot ground on.
Returns: content (the extracted text), url, credits_used, credits_remaining, usage (input_tokens, output_tokens, content_chars, low_content).
Args: url: The URL to extract from prompt: What information to extract (e.g. "list all pricing tiers with features" or "extract the author name and publication date")
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| prompt | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full disclosure responsibility. It goes well beyond basics by stating the 10-credit cost, explaining that the model is not called on low-content pages, describing the low_content flag as a signal, and explicitly warning against fabricated answers. This is strong behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose, then adds a use-case sentence, a critical low-content behavior note, a returned-fields list, and clearly labeled args. Every section earns its place; it is only as long as needed given the important behavioral caveats.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is complete for a two-parameter tool with no annotations and no output schema. It explains when to use it, what it returns, what to gate on, cost implications, and provides argument examples. There is no missing information an agent would need to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It documents both parameters: url, and prompt with concrete examples of extraction tasks. The prompt semantics are enriched with examples, and the URL is at least identified as the target of extraction, which is sufficient for two simple string parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource ('Fetch a webpage and extract specific information using AI') and explicitly frames the tool as returning structured data rather than raw content, which distinguishes it from the sibling fetch tool. It is immediately clear what this tool does and what it is for.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says to use this when you need structured data (e.g. pricing, specs, contact info) 'rather than the raw content', which gives clear usage context relative to fetch. It doesn't mention research/search as alternatives, but the structured-vs-raw contrast provides enough guidance for an agent to select it correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch one or more URLs and return their content as clean markdown. Use this to read articles, documentation, blog posts, or any page where you need the complete text, not just a snippet from search. Also supports PDF, DOCX, and other document formats. Costs 2 credits per URL. Max 10 URLs per request. Failed URLs are not charged.
Set include_raw_html=true to also get the raw HTML source in each result. Useful for inspecting embedded URLs, data attributes, iframes, or script tags that are stripped during markdown conversion. Returns null for non-HTML content (PDF, DOCX, etc.). Same cost.
Returns: results (array of {title, url, content, raw_html, published_time, success, error}), credits_used, credits_remaining.
Args: urls: List of URLs to fetch (max 10) include_raw_html: Include raw HTML source in each result (default false)
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | ||
| include_raw_html | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries the burden, and it delivers. It discloses credit costs per URL, the 10-URL limit, that failed URLs are not charged, the behavior of include_raw_html, and the exact return shape including success and error fields.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well structured and front-loaded: purpose, then costs/limits, then optional behavior, then returns and args. Every sentence provides operational value without filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter tool with no output schema, the description covers everything needed to invoke it correctly: required URLs, max count, cost, raw_html semantics, and the complete return object. No important gap remains for a straightforward fetch operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It adds meaningful semantics for include_raw_html (inspection use cases, null for non-HTML, same cost) and failure charging. The urls argument is still thin, with no mention of URL format, absolute vs relative URLs, or per-item failure behavior beyond cost.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific action ('Fetch one or more URLs and return their content as clean markdown') and clarifies it is for complete text rather than a search snippet. However, it explicitly distinguishes from the search sibling but not from extract or research, so sibling differentiation is incomplete.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit guidance: 'Use this to read articles, documentation, blog posts, or any page where you need the complete text.' The 'not just a snippet from search' phrase implies when search might be preferred, but it does not tell an agent when to choose extract or research instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Perform comprehensive research on a topic. Decomposes your query into sub-queries, searches and reads multiple sources in parallel, then synthesizes a structured report with citations. Best for open-ended or comparative questions that need coverage from many angles. For simple factual lookups, use search instead (optionally with include_answer=true for cheap synthesis). Costs 50 credits.
Returns: query, report (structured markdown with citations), sources (array of {title, url, fetched}), sub_queries (the decomposed queries), credits_used, credits_remaining, usage (token counts).
Args: query: The research question or topic topic: "general" (default) or "news" (prioritize recent news articles) freshness: Filter by recency - "day", "week", "month", "year", or "YYYY-MM-DD:YYYY-MM-DD" max_sources: Maximum number of sources to use, 5-30 (default 20)
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| topic | No | general | |
| freshness | No | ||
| max_sources | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so well. It reveals that the tool decomposes the query into sub-queries, searches and reads multiple sources in parallel, costs 50 credits, and returns specific fields including credits_used and usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is information-dense but well organized, front-loading the core behavior and usage guidance before costs, returns, and parameter docs. The Args and Returns sections make it easy for an agent to scan.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having no output schema or annotations, the description covers purpose, usage criteria, cost, return shape, and all parameter semantics. An agent has sufficient context to decide when to invoke research and how to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, but the tool description compensates fully by explaining every parameter. It defines query, describes topic choices ('general' vs 'news'), gives concrete freshness formats, and specifies max_sources with range and default.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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: 'Perform comprehensive research on a topic' and details the decomposition, parallel reading, and synthesized report with citations. This clearly distinguishes it from siblings like search, extract, and fetch.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says when to use the tool: 'Best for open-ended or comparative questions that need coverage from many angles.' It also points to the alternative for simple cases: 'For simple factual lookups, use search instead,' giving clear when/ when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the web for current information on any topic. Returns extracted page content, not just snippets. Best for factual lookups, specific questions, or when you need a list of sources. For open-ended questions that need synthesis across many sources, use the research tool instead.
For news queries (current events, breaking news, politics, world events), set topic="news" to search news sources specifically. This returns recent articles with publication dates.
Set include_answer=true to get an AI-synthesized answer alongside results (adds 10 credits). This is the sweet spot for most agent tasks, e.g. basic + include_answer = 12 credits, much cheaper than a full 50-credit research call.
Returns: query, answer (if requested), results (array of {title, url, content, description, fetched, published_date}), search_depth, topic, elapsed_ms, credits_used, credits_remaining, altered_query, relaxed_query (set when the query matched nothing and was retried once with its site: operator, else its quotes, removed - the results answer that looser query).
Args: query: The search query search_depth: "basic" (default) for extracted page content (2 credits), "snippets" for SERP snippets only without page fetching (1 credit) max_results: Number of results (default 10, max 20) include_answer: Generate an AI answer that synthesizes the search results (adds 10 credits) include_domains: Only include results from these domains (max 10) exclude_domains: Exclude results from these domains (max 10) topic: "general" for web search, "news" for news articles. use "news" for current events, breaking news, politics, or any time-sensitive query freshness: Filter by recency - "day", "week", "month", "year", or "YYYY-MM-DD:YYYY-MM-DD"
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| topic | No | general | |
| freshness | No | ||
| max_results | No | ||
| search_depth | No | basic | |
| include_answer | No | ||
| exclude_domains | No | ||
| include_domains | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility; it delivers by describing extracted content, optional AI synthesis, credit costs, result shape, and the relaxed_query retry behavior when the original query matches nothing. This is well beyond minimal labeling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but every section has a purpose: purpose/usage intro, news guidance, cost guidance, return structure, and parameter details. Key guidance is front-loaded and formatting is scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 8 parameters, no output schema, and no annotations, the description covers the return object fields, parameter semantics, costs, and fallback behavior. It is complete enough for an agent to select and call the tool correctly without further lookup.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the Args section fully compensates by explaining every parameter, including defaults, choices for search_depth and topic, freshness formats, domain count limits, and cost implications. This transforms bare schema fields into actionable parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool performs a web search for current information and returns extracted page content rather than snippets. The 'Best for factual lookups, specific questions...' framing and reference to the research tool identify its niche among siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says use search for factual lookups, specific questions, or lists of sources, and use research for open-ended synthesis questions. It also gives concrete conditions for choosing topic='news', so an agent knows exactly when to invoke this tool and when not to.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
extractfetchresearchsearchFetch pages as markdown, search web and news, extract structured data. For AI agents.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Web research for agents: quality-scored Google search, webpage extraction, and deep research.
Web data tools for AI agents: pages as markdown, search, maps, commerce, jobs, AI answers.
Add one secure layer between your agents and this server.
