Submit a GPU experiment to the pool and receive a job ID for tracking. Dispatch is governed by your project's policy.
Persist an experiment and return its job ID quickly; existing project policy controls dispatch.
| Name | Required | Description | Default |
|---|---|---|---|
| spec | Yes | ||
| idempotency_key | No |
Changes observed during successful MCP inspections.
v0.1.1Input schema / $defs / CollectionRetryAdded value: +{
+ "additionalProperties": false,
+ "properties": {
+ "initial_backoff_seconds": {
+ "default": 5,
+ "maximum": 3600,
+ "minimum": 0.01,
+ "title": "Initial Backoff Seconds",
+ "type": "number"
+ },
+ "max_attempts": {
+ "default": 12,
+ "maximum": 100,
+ "minimum": 1,
+ "title": "Max Attempts",
+ "type": "integer"
+ },
+ "max_backoff_seconds": {
+ "default": 300,
+ "maximum": 86400,
+ "minimum": 0.01,
+ "title": "Max Backoff Seconds",
+ "type": "number"
+ }
+ },
+ "title": "CollectionRetry",
+ "type": "object"
+}Input schema / $defs / Execution / properties / progress_timeout_minutesAdded value: +{
+ "anyOf": [
+ {
+ "exclusiveMinimum": 0,
+ "maximum": 10080,
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Progress Timeout Minutes"
+}Input schema / $defs / JobSpec / properties / collectionAdded value: +{
+ "$ref": "#/$defs/CollectionRetry"
+}v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It does add a non-obvious behavioral detail: 'existing project policy controls dispatch,' implying persistence happens quickly while actual execution may be deferred or governed externally. However, it does not disclose idempotency behavior, duplicate handling, rejection conditions, or whether the returned job ID guarantees a queued/running job.
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?
The description is a single efficient sentence with no filler, and the core purpose is front-loaded. The second clause adds a useful behavioral caveat, but it is slightly vague and could be more explicit; still, the structure is appropriately compact.
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 tool with a complex nested JobSpec schema, an idempotency_key parameter, no annotations, and no output schema, this description is too sparse. It does not explain how dispatch policy affects the submitted job, what the returned job ID represents, how idempotency works, or what failures might occur, so the agent cannot fully predict invocation consequences.
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%, and the description adds no meaning for the two parameters, spec and idempotency_key. It does not explain that spec is the full JobSpec configuration or describe what idempotency_key is for, leaving the agent to rely only on field names, types, and defaults in the schema.
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 states a specific action ('Persist an experiment') and a concrete result ('return its job ID'), which clearly distinguishes submit_job from siblings like get_job, cancel_job, and list_jobs. The added note that project policy controls dispatch further clarifies that this is the submission entry point, not a record or retrieval operation.
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?
The description gives no explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites such as an existing project, valid experiment, or policy requirements. It does not name any sibling tool or exclusion condition, leaving the agent to infer usage solely from the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.