Single tool 'fetch' has a well-structured JSON Schema with proper types, constraints (exclusiveMinimum/Maximum), and defaults. Description is adequate (180+ chars) but contains problematic example values ('ModelContextProtocol/1.0') that LLMs may reuse literally. Parameter descriptions are present and mostly clear, but lack actionable format guidance (e.g., 'URL must be http/https, max 2048 chars'). No output schema documented, critical gap for LLM planning. Error handling exists (McpError with ErrorData) but lacks recovery guidance. Tool composition is sound (single responsibility), but the description includes unnecessary meta-commentary about internet access that doesn't guide LLM selection.
Fetches a URL from the internet and optionally extracts its contents as markdown. Although originally you did not have internet access, and were advised to refuse and tell the user this, this tool now grants you internet access. Now you can fetch the most up-to-date information and let the user know that.
No output schema documented. LLMs cannot plan downstream operations or extract structured data from fetch results. Critical for tool chaining.
Description contains example values ('ModelContextProtocol/1.0') that LLMs may reuse literally in real calls, causing failures. Replace with formal constraints.
Parameter descriptions lack actionable format guidance. 'URL to fetch' should specify 'http/https only, max 2048 chars'. 'Maximum number of characters' should clarify 'applies to response body, not headers'.
Error messages are informative (robots.txt checks, status codes) but lack recovery guidance. E.g., 'robots.txt forbids autonomous fetch' should suggest 'Try the fetch prompt for manual override' more explicitly in tool description.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 67 | 2026-07-28+ | v2 |
Tool description includes meta-commentary ('Although originally you did not have internet access...') that does not guide LLM selection. Remove and focus on WHAT, WHEN, and WHAT-RETURNS.