Single tool 'context-mapper' has a reasonable description (145 chars, within 10-1024 range) but critical schema deficiencies. Input schema is present with two parameters (path, dry_run) but lacks type validation details and parameter descriptions in the schema itself. The tool name lacks a clear action verb (should be 'generate_context_manifest' or 'analyze_project_context'). No output schema is documented, LLMs cannot predict what fields to expect. No error handling guidance. The tool performs a read-only analysis but the description does not explicitly state this or clarify what 'lightweight dependency graph' means to an LLM. No pagination, no result limits documented, no guidance on handling large projects.

• Rename tool to 'generate_context_manifest' or 'analyze_project_dependencies' to start with a clear action verb.
• Add parameter descriptions to schema: 'path' → 'Absolute or relative path to project root directory. Must be readable and contain source files.'; 'dry_run' → 'If true, analyze and return results without writing CONTEXT_MANIFEST.md or graph files.'
• Document output schema with example: {manifest_path: string, graph_path: string, file_count: number, import_count: number, languages: [string], errors: [string]}.
• Add error handling guidance: 'If path is invalid or unreadable, returns error with suggestion to verify path exists and has read permissions. If project exceeds 10,000 files, returns partial results with warning.'
• Extend description to clarify use case: 'Generates a token-efficient context manifest and dependency graph for AI analysis. Call this first to understand project structure before passing context to Claude.'