RunAPI Seedream MCP server for image generation: create tasks, poll results, and check pricing across 9 model variants from Claude Code, Codex, Cursor, and VS Code.
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 schema structure. Descriptions are present but generic (avg ~80 chars, below 194-char baseline). No error recovery guidance. Tool composition is reasonable (single responsibility), but parameter descriptions are sparse and do not explain constraints or dependencies.
Look up RunAPI pricing for the seedream model line.
Fetch the current status and latest result payload for a seedream task.
Output schemas not documented. Neither tool specifies what fields the response contains, forcing LLMs to infer structure and risking parsing errors.
Parameter descriptions lack actionable constraints. 'task_id' and 'action' in get_task have minimal guidance; 'model' and 'action' in check_pricing do not explain valid values, format, or when defaults apply.
No error recovery guidance. Both tools lack descriptions of failure modes and what the LLM should do if a call fails (retry, lookup alternatives, ask user).
Undocumented parameter dependencies. get_task's 'action' parameter defaults only when there is one asynchronous endpoint; this conditional logic is not explained in the parameter description.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | 2026-07-28+ | v2 |
Missing enum constraints. 'model' and 'action' parameters accept free-form strings instead of enums, inviting hallucinated values. The code builds enums dynamically from contract, but schema does not expose them.