Auto-generate WebMCP tool definitions from any website — no site owner cooperation needed
webmcp-gen auto-generates tool definitions from websites. The 4 tools have basic schemas and descriptions, but critical gaps undermine production readiness. Tool names lack clear verb-noun structure (navigate is vague). The navigate tool has an empty enum for 'page' parameter, making it non-functional. Descriptions are present but generic (10-50 chars), below the 50-200 char LLM-optimized baseline. No output schemas documented. Error handling and recovery guidance absent. The loginUser tool exposes credentials as parameters, violating secret-injection pattern. No tool annotations (readOnlyHint/destructiveHint) despite clear risk classifications. Parameter descriptions are minimal. This is typical of auto-generated definitions, functional but not LLM-optimized.
Authenticate a user with credentials
Navigate to a specific page or section
Search for flights with specified parameters
Submit a support ticket or form
navigate tool has empty enum for 'page' parameter, tool is non-functional. LLM cannot select valid pages.
loginUser exposes username and password as tool parameters. Credentials must never be parameters, use server-side secret injection via environment variables or vault.
Tool descriptions are 10-50 characters, well below LLM-optimized baseline of 50-200 chars. Descriptions lack context for tool selection and do not explain when/why to use each tool.
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields without knowing response structure.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | <=2025-11-25 | v2 |
No tool annotations (readOnlyHint/destructiveHint/idempotentHint) despite clear risk classifications (READ_ONLY, WRITE). Agents cannot reason about side effects.