MCP server for Volcano Engine TLS (Tencent Log Service) integration, providing tools to query log projects and topics
Server has 4 tools with minimal schema documentation and weak descriptions. Tool names lack clear action verbs (describe_* is generic). Input schemas are present but sparse, only project_id and topic_id parameters documented, no type constraints or enums. Descriptions are in Chinese and under 100 chars, lacking WHEN/WHY context. No output schemas documented. No error handling guidance. No parameter descriptions beyond bare names. Composition is reasonable (single responsibility per tool), but overall definition quality is far below production baseline.
通过火山引擎 TLS 获取当前权限下指定项目信息。
通过火山引擎 TLS 获取当前权限下的多个项目信息(限制20个)。
通过火山引擎 TLS 获取当前权限下指定主题信息。
通过火山引擎 TLS 获取当前权限下的多个主题信息(限制20个)。
Tool names use generic 'describe_*' verb instead of action-specific names like 'get_project', 'list_projects'. LLMs cannot distinguish intent from name alone.
Descriptions are in Chinese and under 100 chars, lacking WHAT/WHEN/WHY context. No guidance on when to call describe_project vs describe_projects, or what the output contains.
Input schemas lack type declarations and parameter descriptions. 'project_id' and 'topic_id' have no type field, no format constraint, no description of expected format (UUID? alphanumeric?).
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | <=2025-11-25 | v2 |
No output schemas documented. LLMs cannot plan downstream calls or extract required fields. describe_projects returns 'total' and projects array, but this is not declared in tool definition.
No error handling guidance. Client code checks isError but tool definitions provide no recovery hints. If describe_project fails with 'project not found', LLM has no guidance to call describe_projects first.