Bridge seguro entre Telegram y mcp-dev-core mediante MCP stdio.
9 tools with basic descriptions but critical gaps in schema completeness and parameter documentation. All tools have descriptions (10-50 chars), but most lack detailed parameter descriptions and output schema documentation. No tool annotations (readOnlyHint/destructiveHint). Naming is verb-based but generic (read_*, list_*, run_*). No pagination support despite list_sessions and list_artifacts. Error handling present but not recovery-guided. Schemas visible for 4/9 tools; 5 tools have empty input objects with no parameter documentation.
Create a new session
List available artifacts
List available sessions
Read file contents
Read state snapshot
Read system status information
Run linter
Run test suite
5 tools (read_system_status, read_state_snapshot, run_tests, run_linter, and implicitly others) have empty input schemas {} with no parameter documentation.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). create_session is marked WRITE but lacks destructiveHint annotation in schema. Agents cannot infer safety/retry semantics.
list_sessions and list_artifacts lack pagination (no limit default, no offset/cursor, no total_count in response).
Parameter descriptions missing or minimal. 'limit' in list_sessions has description but no min/max bounds. 'metadata' in create_session is vague ('Session metadata including source, chatId, and correlationId'), does not specify required fields, types, or format.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2025-06-18+ | v2 |
Search codebase for text matches
Output schemas not documented in tool definitions. Agents cannot plan downstream calls or extract required fields (e.g., does list_sessions return activeSessionId? Does search_codebase return file paths for chaining to read_file?).