Create a persistent OpenCode agent session

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

Beyond the minimal openWorldHint annotation, the description discloses meaningful behavior: the session is persistent, no task runs on creation, and the agent's context is retained between calls when used with send_message. This adds real behavioral context beyond what the structured annotation provides.

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?

Two sentences with zero filler. The core purpose and scope are front-loaded in the first sentence, and the second sentence earns its place by explaining the interaction protocol with send_message.

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 simple create operation with a fully documented schema, the description is mostly sufficient. However, with no output schema and an openWorldHint, it would help to state what the call returns (e.g., a session identifier to use with send_message) and any workspace requirements, so an agent is left with a small gap about the response.

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 100%, so the input schema already documents all four parameters. The description adds no parameter-level meaning, so the baseline of 3 applies; nothing is missing, but nothing extra is contributed either.

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 (create), a specific resource (persistent delegation session in a workspace), and a critical constraint ('without running a task yet'). This last phrase directly distinguishes it from the sibling delegate_task, so an agent can tell the tools apart without opening schemas.

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 gives a clear workflow context: create the session first, then follow up with send_message to keep the agent's context across calls. It does not explicitly name delegate_task as the alternative for one-shot task execution or state when not to use this tool, so it stops short of full when/when-not guidance.

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