Loading ToolBench
Model Context Protocol server for Couchbase database operations
Server has 8 tools with basic naming and descriptions, but significant gaps in schema completeness and parameter documentation. Tool names follow verb_noun convention (get_, test_, upsert_, delete_, run_) which is good. However, most tools lack detailed parameter descriptions and output schemas are not documented. Descriptions are present but generic (avg ~100 chars, below the 194-char baseline). No error handling guidance, no pagination support for list operations, and no tool annotations (readOnlyHint/destructiveHint). STDIO transport caps overall score at 50; definition quality alone would be ~52.
Delete a document by its ID. Returns True on success, False on failure.
Get a document by its ID from the specified scope and collection. If the document is not found, it will raise an exception.
Get the schema for a collection in the specified scope. Returns a dictionary with the collection name and the schema returned by running INFER query on the Couchbase collection.
Get the names of all scopes and collections in the bucket. Returns a dictionary with scope names as keys and lists of collection names as values.
Get the server status and configuration without establishing connection. This tool can be used to verify if the server is running and check the configuration.
No output schemas documented. Tools return results but LLMs cannot predict field structure, forcing them to parse responses blindly. This violates pattern:tool and pattern:response-shaper.
Parameter descriptions are minimal or missing context. E.g., 'scope_name' and 'collection_name' lack explanation of what these are or how to discover valid values. Violates pattern:tool-description.
No error handling guidance. Tools state 'Returns True on success, False on failure' but do not explain what failures are possible, when to retry, or how to recover. Violates pattern:recovery-guide.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 57 | <=2025-11-25 | v2 |
Run a SQL++ query on a scope and return the results as a list of JSON objects.
Test the connection to Couchbase cluster and bucket. This tool verifies the connection to the Couchbase cluster and bucket by establishing the connection if it is not already established. Returns connection status and basic cluster information.
Insert or update a document by its ID. Returns True on success, False on failure.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Risk levels are declared in metadata but not in tool definitions. LLMs cannot infer which tools are safe to retry or which modify state.
run_sql_plus_plus_query accepts free-form SQL with no input validation or injection guards. Description does not warn about SQL injection risk or mention read-only mode enforcement. Violates pattern:tool-gateway.