Loading ToolBench
MCP server that bridges Foggy Query Models with Odoo, providing tools for querying Odoo data models, listing available models, and describing model schemas with permission-based filtering
Three tools with minimal schema documentation and generic descriptions. No output schemas visible. Tool names use underscores (dataset__query_model) which is acceptable but descriptions are too brief (avg 95 chars, below 194-char baseline). No error handling guidance, no pagination support for list_models, no parameter constraints. Schema definitions exist but are skeletal (only 'model' param with type string, no format/pattern/enum). No evidence of idempotency, confirmation patterns, or recovery guidance.
Get detailed schema information for a Foggy Query Model, including field definitions, data types, and physical table mappings
List all available Foggy Query Models accessible to the current user based on ir.model.access permissions
Query a Foggy Query Model (QM) to retrieve data from Odoo
Parameter descriptions missing. All three tools have input schemas with 'model' parameter but no description of what the model name should be, format, or how to discover valid names.
No output schemas documented. LLMs cannot plan downstream calls or extract required fields without knowing what these tools return.
Tool descriptions too brief and lack context. 'Query a Foggy Query Model' (35 chars) does not explain when to use this vs describe_model, what data it returns, or prerequisites. Baseline is 194 chars.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | 2025-06-18+ | v2 |
No error handling guidance. No indication of what errors are retryable, what user-fixable errors look like, or recovery steps (e.g., 'If model not found, call dataset__list_models first').
dataset__query_model lacks pagination parameters (limit, offset, page_size). Large result sets will blow context windows without pagination support.