Get a grounded answer with inline [n] citations: searches the web, fetches sources, and answers strictly from them. Price: $0.05
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The question to answer | |
| sources | No | Web sources to search, fetch, and cite (1-5, default: 3) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the burden of disclosing behavior. It states the tool searches the web, fetches sources, and 'answers strictly from them,' which indicates a read-only, source-grounded behavior. It also discloses the cost ('Price: $0.05'), a key side effect. It does not mention rate limits or edge cases, but for a simple question-answering tool, this is adequate.
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 two sentences and every part earns its place: the main purpose, the process, and the price. It is front-loaded with the most important information ('Get a grounded answer with inline [n] citations') and contains no fluff.
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?
Given the tool's simplicity (2 parameters, both documented) and lack of output schema, the description sufficiently conveys what the return value is: an answer with inline citations. It also explains the underlying process. However, it could be slightly more explicit about the exact output structure (e.g., answer text and citation list), so a 4 is appropriate.
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 schema documentation already covers 100% of the parameter meanings: query is 'The question to answer' and sources includes range and default. The description adds no additional parameter-specific details beyond the schema, so the baseline of 3 applies.
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 clearly states the tool's action: 'Get a grounded answer with inline [n] citations.' It specifies the resource (web sources) and the process (searches, fetches, answers strictly from them). This distinguishes it from sibling search tools like search_web (which merely returns results) and deep_research (which implies broader research).
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?
The description provides clear context for when to use the tool: when a grounded, cited answer is needed. It implies the tool synthesizes information from multiple sources rather than just fetching or searching. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tool clusters have near-overlapping purposes: fetch_webpage/fetch_webpage_pro/fetch_resilient and batch_fetch/get_contents are hard to distinguish, and answer_question/research/deep_research differ mainly in price and depth. The search_* and intel_* families are clearer, but the core fetching and research overlap creates ambiguity.
Most tools follow a verb_noun snake_case pattern (fetch_webpage, search_web, extract_data), but there are notable exceptions like domain_intel, package_intel, youtube_transcript, memory_set, and intel_company, where the prefix/suffix convention is inconsistent. Still, the naming is broadly readable.
35 tools is a large surface, far beyond the typical 3-15 range. The server covers many research verticals, but the number feels bloated, especially with multiple fetch and research variants that could be consolidated.
The tool set covers a wide range of web research needs: searching, fetching, crawling, extracting, screenshots, domain/tech/package intelligence, and market/competitive analysis. It lacks obvious lifecycle operations for monitors (list/delete/update) and memory (get/delete), but core workflows are well covered.