A Model Context Protocol server that provides tools to fetch and manage Toggl Track data.
Server has 9 tools with complete schemas and descriptions. Naming follows verb_noun convention (get_, create_, update_, delete_, stop_). Descriptions are present but brief (avg 60 chars, below 194-char baseline). All parameters have type definitions and descriptions. However, output schemas are not documented, responses are formatted as JSON strings rather than structured objects. Error handling is minimal; no recovery guidance or actionable error messages. No tool annotations (readOnlyHint/destructiveHint) despite clear risk levels. Parameter validation exists (ISO datetime checks) but error messages are generic. Missing pagination documentation for list tools despite accepting page/perPage params.
Create a new time entry in a workspace
Delete a time entry
Get the currently running time entry for the authenticated user
Get time entries for the current user with optional filters
Get clients for a workspace
Get tags for a workspace
List workspaces accessible to the authenticated user
Output schemas not documented. Tools return JSON strings via _format_response() rather than structured objects. LLMs cannot infer response field names or types for downstream tool chaining.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Tools are marked with Risk levels in metadata but not exposed via MCP tool annotations. Agents cannot determine which tools are safe to retry.
Error handling lacks recovery guidance. Validation errors (e.g., 'startDate is not a valid ISO 8601 datetime') are raised but do not suggest corrective actions. API errors from _execute_api_request() are not caught or enriched.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 57 | 2026-07-28+ | v2 |
Stop a running time entry
Update a single time entry
Pagination not fully documented. get_workspace_tags and get_workspace_clients accept page/perPage but tool descriptions do not mention pagination behavior, total count, or result limits.
Descriptions are brief (avg 60 chars vs 194-char baseline). E.g., 'Get tags for a workspace' lacks context on when to call this tool or what structure it returns. Descriptions should be 50-200 chars and answer WHAT, WHEN, and WHAT IT RETURNS.