opencode_batch

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It reveals the parallelism cap (up to 3) and the dependency mechanism, which are useful behavioral traits. However, it does not disclose what happens on partial failure (do successful tasks get killed?), whether parallel sessions compromise resource use, or what the return value/status reporting looks like. Given a launch tool with no annotations, more behavioral detail would be expected.

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 declarative sentence that is efficient and front-loaded with the core purpose. It captures the most important constraints (parallelism limit, dependency support) without waste. The compact wording earns every word.

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 batch/parallel execution tool with a nested-object parameter and no output schema, the description could be richer. It explains the core mechanism (parallelism + dependencies) but omits expected return/status semantics, failure behavior, or how results are retrieved (e.g., via opencode_batch_status). While the parameter schema is fully documented, the tool's overall operational behavior is somewhat underspecified given its complexity.

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 schema documents all fields including task, depends_on, model, workdir, auto_approve, and agent. The description adds the significance of depends_on (referencing 'Session ID or task_N index that must complete first') and the 3-session concurrency limit, which enriches the tasks parameter meaning. However, it does not clarify field interactions like whether auto_approve or model apply per-task, so value over schema is moderate.

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 clear purpose: 'Starts up to 3 parallel OpenCode sessions with dependency support.' The verb 'Starts' plus the resource (OpenCode sessions) and the key constraint (up to 3 parallel, dependency support) are all conveyed. It distinguishes from siblings like opencode_start (single session) and opencode_batch_status by mentioning parallelism and dependencies, though it could more explicitly contrast with those siblings.

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 implies usage for parallel execution via 'up to 3 parallel sessions' and 'dependency support,' which signals when to use this tool (when running multiple tasks concurrently). However, it does not explicitly state when NOT to use it or point to alternatives like opencode_start for single tasks. The 'dependency support' mention hints at sequencing use cases but stops short of explicit guidance.

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