Two tools with minimal descriptions and incomplete parameter documentation. get_task has a 73-char description (below baseline 194 chars); check_pricing has 60 chars. Both parameter descriptions are present but terse. No output schemas documented. No error handling guidance. Tool names follow verb_noun pattern but lack context about what data is returned or when to use each tool. No tool annotations (readOnlyHint, etc.) despite both being read-only operations.

• Expand get_task description to ~150 - 200 chars: 'Fetch the current status and latest result payload for an InfiniteTalk video generation task. Returns task status (pending, processing, completed, failed), output URLs, and error details if applicable. Use this to poll task progress after creating a task.'
• Expand check_pricing description: 'Look up current RunAPI pricing for the InfiniteTalk model line. Returns per-unit cost (USD) for the specified model and endpoint. Use this before creating tasks to estimate costs.'
• Document output schemas in tool descriptions or via a separate schema field. E.g., 'Returns: {task_id, status, task: {id, status, result, error, created_at, updated_at}}'
• Add error handling guidance: 'If task not found, verify task_id and action endpoint. If pricing lookup fails, check model and action parameters against available options.'
• Add readOnlyHint: true to both tool schemas to signal they are safe to call repeatedly without side effects.