submit_job

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

The description adds useful async behavior beyond the annotations: it returns a job_id immediately and requires polling job_status for progress and the result. It also names the supported tools, reinforcing the read-only scope already declared by readOnlyHint=true and destructiveHint=false.

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 three tight sentences with no waste. It front-loads the core async read-only purpose, then lists supported tools, then explains the return-and-poll behavior.

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 nested-arguments async submission tool with no output schema, the description covers the essential call flow: choose a supported tool, pass its arguments, receive a job_id, and poll job_status. It does not mention cancel_job or failure behavior, but it is complete enough for correct selection and invocation.

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?

The schema already documents the tool enum and the arguments object, and the description mainly repeats the supported tool names. Its note that arguments use the same names as the selected tool's direct call adds some helpful meaning for the nested arguments object, but it does not detail per-tool argument requirements.

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 and resource: starting a background job for one of three named analysis tools. It clearly distinguishes the async submission role from the sibling job_status polling role, though it does not explicitly contrast with calling quality_report, validate_dataset, or quality_gate directly.

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?

It explains when this tool is appropriate by saying it starts a long-running read-only analysis in the background and that job_status should be polled for progress and results. It names the supported analysis tools but does not explicitly state when to avoid submit_job in favor of direct synchronous calls.

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