Submit Batch

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already disclose readOnly=false, idempotent=false, openWorld=true, destructive=false, so the description needn't restate safety. But it adds almost nothing beyond 'keep a manifest' — no mention of async/non-blocking behavior, whether a handle is returned for later polling, or side effects. For a non-idempotent submission entry point with no output schema, this is a notable gap.

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?

A single front-loaded sentence with no filler. It is efficient, though its brevity borders on under-specification rather than true conciseness.

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 batch submission tool with no output schema and no clarifying annotations on return behavior, the description should explain what submission yields and how it relates to the polling/collection siblings. It leaves the agent unable to predict the response or next step.

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?

With only 50% schema coverage, source_path is undocumented in the schema; the description's 'one schematic' weakly implies source_path points to a schematic, but it doesn't clarify format or whether it's a file, project, or identifier. workspace_root is already covered by the schema. Value added is minimal.

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?

It has a clear verb (Run) and resource (one schematic), and 'manifest of the artifacts' hints at a tracked submission, which separates it from cancel_batch/collect_batch_results/get_batch_status. However, the name 'submit_batch' and the description's 'one schematic' conflict about whether this handles a batch or a single item, leaving scope ambiguous.

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 submit vs. when to poll (get_batch_status) or collect (collect_batch_results), and no prerequisites or sequencing hints despite an obvious batch lifecycle among siblings. The agent must infer the workflow entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.