Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and error handling. get_task has optional parameters with minimal guidance on defaults and dependencies. check_pricing lacks clarity on what 'model' and 'action' mean in context. Neither tool documents output structure or error recovery paths. Descriptions are present but generic (10-20 chars above minimum). No tool annotations, no idempotency hints, no permission scopes declared. Parameter descriptions exist but are terse and lack format/constraint guidance.

• Add explicit output schema documentation to both tools. For get_task, document the structure of the 'task' object (fields, types, example). For check_pricing, specify pricing response fields (cost_per_unit, currency, effective_date, etc.).
• Enhance parameter descriptions with format and constraint guidance. E.g., 'task_id: UUID returned from task creation (e.g., 550e8400-e29b-41d4-a716-446655440000)' and 'action: Endpoint name (e.g., generate, upscale). Defaults to the primary endpoint if only one exists.'
• Add error recovery guidance in descriptions. E.g., 'If task not found, verify task_id is correct and task has not expired (tasks expire after 7 days).' For pricing, 'If model not found, call list_models first to see available options.'
• Implement tool annotations via MCP SDK. Mark both tools with readOnlyHint=true and idempotentHint=true so agents know they are safe to retry and cache.
• Rename 'check_pricing' to 'get_pricing' for clarity and consistency with verb_noun naming convention. Update description to specify what pricing data is returned (e.g., 'Fetch current per-unit cost and billing model for a RunAPI model.').