oc_task_start

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

The description discloses key behavioral traits: it returns a task_id, the result is persisted to disk, and it survives MCP-session loss. These add context beyond the annotations (which only have false hints). No contradiction with annotations is present.

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 extremely concise (two sentences) and front-loaded with the primary action. Every sentence provides essential information about purpose, return value, and durability, with no wasted words.

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?

Given the tool's complexity (5 parameters, no output schema, minimal annotations), the description covers the two use cases and the return value. It could be enhanced by explaining the task lifecycle or error handling, but it is sufficiently complete for an agent to understand its basic functionality.

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?

While the input schema already describes all 5 parameters, the description adds meaningful context for the 'kind' parameter by explaining the effect of omitting it ('creates a task envelope for host-driven browser tool calls'). This adds value beyond 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 clearly states the tool's two purposes: creating a task-level browser harness envelope or launching a long-running tool as a background task. It uses specific verbs ('Create', 'launch') and resource ('task-level browser harness envelope', 'background task'), and distinguishes from sibling oc_task_* tools by explaining the polling/cancellation workflow.

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 explains when to use the tool (for background tasks or host-driven browser tool calls) and mentions related polling tools (oc_task_get, oc_task_list, oc_task_wait, oc_task_cancel). However, it does not explicitly state when not to use it or provide alternatives for synchronous execution, leaving a minor gap.

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