opencode_start

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

No annotations provided, so description carries the burden. It discloses that sessions emit events (running, idle, waiting_input, done, stale, contract_violated) and describes the notification-watcher pattern, which is good context. However, it doesn't disclose side effects (e.g., potential cost/session creation overhead, async behavior details, whether it blocks) beyond the event flow. Some behavioral detail is given but not exhaustive.

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, front-loaded with purpose and key return values, then concise workflow. No wasted words. Slightly dense in sentence two (lists 7 event types inline) but efficient overall.

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?

With 12 params including a nested contract object and complex lifecycle, this is a complex tool. The description explains startup and event-driven flow but not the contract semantics, session continuation behavior, or contract_violated triggering conditions in detail. No output schema to fill gaps. Adequate but leaves room for more on the lifecycle/state machine.

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 all 12 parameters have individual descriptions already. The description adds workflow context (events_log_path usage, follow-up calls) but doesn't explain parameter relationships or the contract object semantics beyond schema. Baseline 3 is appropriate given the high schema coverage; description adds minimal param value.

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?

Description clearly states spawns a new OpenCode CLI session and starts the initial task, with specific verb (spawns/starts), resource (OpenCode CLI session), and returns session_id and events_log_path. It distinguishes from siblings like opencode_health, opencode_read, opencode_kill by its unique starting role.

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?

Provides clear workflow guidance: watch events_log_path for notifications, call opencode_read when notified, then opencode_kill when done. It names the follow-up tools by name. However, it doesn't explicitly state when NOT to use this tool or when to prefer an alternative like opencode_continue/switch, though the usage flow is well-clarified.

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