MCP server for OMOTG Telegram bot that bridges Telegram to OpenCode agent platform with SSE transport
Two tools with complete input schemas and descriptions. Naming follows verb_noun convention (send_telegram_*). Descriptions are adequate (60-90 chars) but lack context on when to use each tool or what happens on failure. Parameters are typed and described, but lack enums for constrained values (parse_mode, status). No output schema documented. Error handling returns generic strings without recovery guidance. Missing idempotency hints for write operations.
Send a text message to a Telegram chat
Send a formatted notification (emoji + status + message) to a Telegram chat
parse_mode and status parameters accept free-form strings instead of enums. LLMs may hallucinate invalid values like 'HTML5' or 'pending' instead of constrained options.
No output schema documented. Callers cannot predict response structure or extract fields for downstream tool calls.
Error responses are generic strings ('telegram error: ...') without recovery guidance. LLM cannot determine if error is retryable or user-fixable.
Tool descriptions do not indicate these are write operations with side effects. LLMs need explicit 'modifies state' language to reason about retry safety and idempotency.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 58 | <=2025-11-25 | v2 |
No distinction between the two tools in descriptions. Both send messages; send_telegram_notification adds emoji/status formatting. Descriptions should clarify when to use each.