Polls a RunningHub task until it completes or times out, returning result file URLs.
轮询等待 RunningHub 任务完成（每 5 秒查询一次，直到 SUCCESS / FAILED 或超时）。返回结果文件 URL 列表。
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | Yes | 任务 ID | |
| apiVersion | No | 查询接口版本：v2=标准模型 API 任务（/openapi/v2/query）；legacy=工作流/AI应用任务（/task/openapi/outputs）。不确定时先试 v2，失败再用 legacy | v2 |
| timeoutSec | No | 最长等待秒数，默认 600 | |
| intervalSec | No | 轮询间隔秒数，默认 5 |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose useful traits: the polling cadence, the terminal states (SUCCESS/FAILED), the timeout bound, and the return shape (URL list). It omits what happens on timeout (error vs partial result) and any auth/quota requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences: the first front-loads the polling/wait behavior and termination conditions, the second states the return value. No filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description correctly supplies the return shape (list of result file URLs). Combined with 100% schema coverage and the disclosed polling/timeout behavior, an agent has what it needs; only timeout-failure semantics are missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the schema itself richly documents apiVersion (with endpoints and fallback advice), timeoutSec, and intervalSec. The description only echoes the 5-second interval, adding no meaning beyond the structured fields, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb (poll/wait) and resource (RunningHub task) plus the completion condition. It implicitly separates itself from the single-shot runninghub_query_task by describing polling-until-terminal-state, though it never names that sibling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: an agent infers it should call this when it wants to block until completion. There is no explicit statement of when to prefer this over runninghub_query_task, and no exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.