jules_wait_for_task

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

With no annotations, the description carries the full burden, and it does disclose key behavior: blocking/polling, the terminal conditions it waits for, and the async-to-harness bridging. However, it does not disclose what the tool returns, whether it exits with partial states, or what happens on timeout or when a session is not found.

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 compact and front-loaded, with the core polling/waiting behavior stated first. The second sentence adds useful architectural context, though it is slightly abstract and not strictly necessary.

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?

The description covers what the tool waits for, and parameter documentation is complete, but the absence of an output schema or any mention of return values leaves an important gap. An agent invoking a blocking wait tool would benefit from knowing what result shape or status it receives when the wait ends.

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%, so the schema already documents all five parameters clearly. The description adds minimal value beyond that, though it does contextualize the plan approval and question-asking states that relate to auto_approve_plan and auto_unblock_questions.

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 clearly identifies the action (poll/wait), the resource (a Google Jules session), and the stopping conditions (completion, failure, plan approval request, or question asking). It also hints at its differentiating role by bridging async cloud execution into the harness, though it does not explicitly name sibling tools.

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 context is implied: it is for synchronously waiting on an already-running async Jules session. However, there is no explicit guidance on when to choose this over alternatives like jules_stream_progress, jules_check_events, or jules_dispatch_and_wait, nor any when-not-to-use guidance.

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