Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and error handling guidance. get_task has optional parameters with minimal context; check_pricing lacks clarity on defaults and return structure. Neither tool description explains when to use it vs alternatives or what happens on failure. No output schemas documented. Parameter descriptions are present but sparse (avg 45 chars vs baseline 72). No error recovery guidance. Tools are read-only (good) but lack the depth expected for production use.

• Document output schemas for both tools. Example: get_task returns {task_id, status, task: {id, status, result, created_at, updated_at}}. check_pricing returns {model, endpoint, pricing: {cost_per_call, currency, effective_date}}.
• Expand parameter descriptions with format and discovery hints. E.g., 'task_id: UUID returned by create_task or similar. Example: 550e8400-e29b-41d4-a716-446655440000' and 'model: Model slug (e.g., flux-pro, flux-realism). Call list_models() to discover available options.'
• Add error recovery guidance to tool descriptions. E.g., 'If task_id is not found, verify the ID and check that the task was created on the specified endpoint. If pricing lookup fails, fall back to the pricing_url provided in the response.'
• Clarify default behavior for optional parameters. If action defaults to 'the line's only asynchronous endpoint', document the actual endpoint name or provide an enum of valid values.
• Explain the pricing response format and use case. E.g., 'Returns current pricing for the specified model/endpoint. Use this to estimate costs before creating tasks or to inform users of per-call charges.'