Loading ToolBench
MCP server for web search with full page content extraction, search summaries, and single page content extraction
Two tools with complete input schemas and descriptions. Naming follows verb_noun pattern (full-web-search, get-web-search-summaries). Descriptions are clear and differentiate use cases well (194 - 220 chars, within baseline 34 - 392 range). Parameters have types, descriptions, and constraints (min/max). However, output schemas are not documented in the source code provided, critical for LLM planning. No error handling guidance visible. No tool annotations (readOnlyHint, etc.). Risk classification present but not integrated into descriptions.
Search the web and fetch complete page content from top results. This is the most comprehensive web search tool. It searches the web and then follows the resulting links to extract their full page content, providing the most detailed and complete information available. Use get-web-search-summaries for a lightweight alternative.
Search the web and return only the search result snippets/descriptions without following links to extract full page content. This is a lightweight alternative to full-web-search for when you only need brief search results. For comprehensive information, use full-web-search instead.
Output schemas not documented. LLMs cannot plan downstream tool calls or extract structured data without knowing what fields to expect (e.g., does full-web-search return url, title, content, metadata?).
No error handling guidance. If a search fails or returns no results, the tool should guide the LLM on recovery (e.g., 'No results found. Try a simpler query or different keywords.').
Tool annotations missing. Both tools are read-only (Risk: READ_ONLY noted), but this is not declared via readOnlyHint in the schema. LLMs cannot infer safety properties without explicit annotations.
Parameter 'maxContentLength' description says 'Usually not needed, content length is automatically optimized' but does not explain what happens if the limit is exceeded or how optimization works. Ambiguous guidance.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2026-07-28+ | v2 |
No pagination or result-limiting guidance in descriptions. If full-web-search returns 5 results with full page content, each potentially thousands of tokens, the LLM may not understand context cost. Baseline pattern requires pagination and result caps.