Loading ToolBench
A Model Context Protocol server for CData SurveyMonkey connector that provides tools to query and retrieve table metadata and column information from SurveyMonkey data sources via JDBC
The SurveyMonkey MCP server provides three read-only tools for data discovery and SQL execution. All tools have descriptive names that follow verb_noun conventions and clear descriptions. However, there are notable gaps in parameter documentation, missing output schema definitions, and lack of error handling guidance. The tools are well-structured around a data access pattern but fall short of production-grade quality due to incomplete parameter descriptions and missing schema documentation.
Retrieves a list of fields, dimensions, or measures (as columns) for an object, entity or collection (table). Use the `surveymonkey_get_tables` tool to get a list of available tables. The output of the tool will be returned in CSV format, with the first line containing column headers.
Retrieves a list of objects, entities, collections, etc. (as tables) available in the data source. Use the `surveymonkey_get_columns` tool to list available columns on a table. Both `catalog` and `schema` are optional parameters. The output of the tool will be returned in CSV format, with the first line containing column headers.
Execute a SQL SELECT statement.
Output schemas are not documented. Tools return CSV-formatted text without defining the structure agents should expect (column names, data types, row format). LLMs cannot reason about downstream processing or field extraction.
Parameter descriptions are minimal or absent in some cases. The 'catalog' and 'schema' parameters lack explanation of when they are required vs optional, what they control, or how they map to the underlying SurveyMonkey API.
No error handling or recovery guidance. All three tools throw generic RuntimeException on failure with minimal context. LLMs cannot determine if an error is retryable, user-fixable, or fatal.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 46 | <=2025-11-25 | v2 |
| 2026-03-09 | F | 45 | - | v1 |
surveymonkey_run_query description lacks guidance on SQL constraints and error conditions. It mentions 'Valid clauses' but does not explain what happens if an agent writes unsupported SQL (e.g., CREATE TABLE, UPDATE, DELETE). No mention of pagination or result limits.
No documentation of result limits or pagination. If a query returns thousands of rows, the tool will dump all of them as CSV, potentially exhausting LLM context windows. No offset/limit parameters or guidance on result caps.