start_plan

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

Annotations already declare readOnlyHint=true, and the description consistently presents this as a preview operation. It adds useful async context by noting that the tool runs in the background and returns a job ID, but it does not explain job lifecycle, polling, or cancellation behavior.

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 front-loaded sentence with no wasted words. It efficiently conveys the core async behavior and return value.

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 two-parameter asynchronous tool with no output schema and no schema descriptions, the definition is too sparse. It should explain the parameters and indicate how the returned job ID is used, such as with get_job_status or cancel_job.

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 both optional parameters, and the description does not mention environment or select_models at all. With low coverage, the description should compensate, but it provides no parameter meaning.

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 outcome: starting a plan preview in the background and returning a job ID. It is clear what the tool does, but it does not distinguish it from siblings such as plan, apply_plan, or start_run.

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?

There is no explicit guidance on when to use this tool versus alternatives. The phrase 'in the background' weakly implies an asynchronous workflow, but it does not mention polling with get_job_status or choosing this over plan/start_run.

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