Loading ToolBench
Comprehensive, highly performant Google Workspace Streamable HTTP & SSE MCP Server for Calendar, Gmail, Docs, Sheets, Slides & Drive
Server has 7 tools with basic schemas and descriptions. All tools have descriptions (10-50 chars, mostly adequate). Input schemas are present with type definitions and parameter descriptions. However, several critical gaps: (1) 'service' and 'chat_service'/'people_service' parameters are typed as 'object' with minimal description, these appear to be injected dependencies, not user inputs, yet are exposed in schemas; (2) output schemas are completely undocumented, LLMs cannot plan downstream calls without knowing what fields are returned; (3) error handling descriptions are absent; (4) no pagination guidance in list_spaces/get_messages despite accepting page_size; (5) parameter constraints (e.g., valid space_type values) are mentioned in descriptions but not formalized as enums. Tool names follow verb_noun pattern well (list_, get_, create_, update_). Composition is reasonable, each tool has a single responsibility. Missing: recovery guidance, actionable error messages, and output schema documentation.
Creates a new Apps Script project.
Retrieves messages from a Google Chat space.
Retrieves content of a specific file within a project.
Retrieves complete project details including all source files.
Lists Google Apps Script projects accessible to the user. Uses Drive API to find Apps Script files.
Lists Google Chat spaces (rooms and direct messages) accessible to the user.
Output schemas completely undocumented. LLMs cannot infer what fields are returned by any tool, blocking downstream tool chaining and forcing exploratory calls.
Injected service parameters ('service', 'chat_service', 'people_service') exposed in input schemas as 'object' type with minimal description. These are server-side dependencies, not user inputs. Should be hidden from the schema or clearly marked as internal.
Enum constraints mentioned in descriptions but not formalized in schema. 'space_type' accepts 'all', 'room', 'dm' per description, but schema lacks enum declaration. LLMs cannot validate options without formal constraints.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 62 | <=2025-11-25 | v2 |
Updates the content of files within an Apps Script project.
Pagination parameters (page_size, page_token, order_by) present but no guidance on total count, next_cursor, or result limits. LLMs cannot determine when to stop paginating or how many results to expect.
No error handling guidance. Tools lack descriptions of failure modes, recovery steps, or actionable error messages. LLMs cannot self-correct on failures.