Single tool 'webrecon_scan' has a basic description (58 chars) but critically lacks parameter descriptions and output schema documentation. Input schema exists but is minimal: only 'target' string with no format constraints, range limits, or usage guidance. No error handling guidance, no examples of expected output structure, and no documentation of what 'findings' contains. The tool description states 'Returns JSON findings' but does not document the JSON structure, field names, or types. This forces LLMs to guess at output shape and invites misuse.

• Add description to 'target' parameter: 'Target URL or file path to scan for web technologies, CMS, and frameworks. Accepts http://, https://, or local file paths. Max 2048 characters.'
• Document output schema in tool description: 'Returns JSON object with fields: {tool: string, findings: [{id: string, sev: string, where: string}], score: number}. Findings array contains detected technologies sorted by severity.'
• Add error handling guidance: 'If target is unreachable, returns error with message. If target is invalid format, returns validation error. Retry with valid URL or path.'
• Rename tool to 'fingerprint_web_technologies' or 'detect_web_stack' for clarity and to avoid confusion with generic 'scan' tools.
• Add constraints to 'target' parameter: specify accepted formats (URL pattern, file path pattern), max length, and whether relative paths are supported.