submit_taskSend a task prompt to a remote scientific agent, optionally uploading local files from the working directory (max 100 MB each), to run the task and return results.
提交任务到远程 Agent（支持文件上传）
input_files 为本地文件路径列表，只能上传当前工作目录下的文件，单个文件不超过 100MB。
| Name | Required | Description | Default |
|---|---|---|---|
| server | No | ||
| service_id | Yes | ||
| session_id | No | ||
| input_files | No | ||
| task_prompt | Yes | ||
| output_prompt | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.6Input schema / properties / server / defaultPrevious value: -"default"New value: +""v0.1.3v0.1.2v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so the description carries the full burden. It does disclose meaningful operational constraints (files must be under the current working directory, 100MB per-file cap), which is real value, but it omits whether submission is async, whether it returns a task id to poll, and any auth/service 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 compact sentences, front-loaded with the core action followed by the file-upload constraint. No filler, though the constraint is scoped only to one parameter.
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?
For a 6-parameter async-style submission tool with zero schema coverage and no annotations, the description is too thin: it explains one parameter's constraints but not session reuse, service selection, or expected flow (submit → poll). The output schema covers return values, but the invocation contract is largely unexplained.
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 description coverage is 0% for 6 parameters, so the description must compensate. It only explains input_files; server, service_id, session_id, task_prompt, and output_prompt remain entirely undocumented, leaving the agent to guess at the most important required fields.
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?
States a specific verb+resource: submit a task to a remote Agent, with the extra capability of file upload. It is distinguishable from the read/cancel siblings (get_task, poll_task, cancel_task) by the 'submit' action, though it never explicitly contrasts with them.
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?
No guidance on when to use this versus poll_task/get_task or when a new submission is warranted versus continuing a session_id. Only a constraint on file inputs is given, not usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.