Add your description here
This server has critical definition gaps. All three tools lack parameter descriptions (required by pattern:tool-description). Tool descriptions are minimal (10-34 chars, below the 50-200 char baseline for LLM-optimized descriptions). No output schemas are documented. The DatabaseConfig class is defined but not exposed as a structured return type in the tool signatures. Error handling is absent, no guidance on what happens if database.json is missing, malformed, or if a lookup fails. The server reads from a local JSON file with no validation, no pagination, and no error recovery.
return all database config
return all database name
return database config by database name
No parameter descriptions. get_database_config_by_name accepts 'database_name' but provides no description of what format is expected, whether it is case-sensitive, or what happens if not found.
No output schema documentation. Tools return DatabaseConfig objects or lists, but the schema is not declared in tool definitions. LLMs cannot infer what fields are available (name, host, port, username, password, database, db_system).
Minimal tool descriptions (10-34 chars). Descriptions like 'return all database config' do not explain WHEN to use the tool, what it returns, or how it differs from similar tools. Baseline is 50-200 chars for LLM-optimized descriptions.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 32 | 2026-07-28+ | v2 |
No error handling or recovery guidance. If database.json is missing, malformed, or a database name is not found, the tool will crash or return None with no actionable error message for the LLM.
Credentials exposed in response. DatabaseConfig includes username and password fields returned to the LLM. These should never be exposed in tool responses, they enter the LLM context and risk being logged or echoed to users.