par

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

No annotations exist, so the description must disclose behavior. It covers the core parallel execution and default concurrency, but lacks details on failure handling, timeouts, resource limits, or result aggregation, which are important for a parallel execution tool.

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 very concise: a two-sentence overview followed by parameter descriptions. It is front-loaded with the main purpose and every sentence adds value without redundancy.

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 (parallel execution) and that an output schema exists, the description should explain what the tool returns. It omits return value details, error behavior, and concurrency limits beyond the default, leaving gaps for an agent.

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 coverage is 0%, but the description adds rich semantics: explains that 'tasks' is a JSON array supporting all sandbox fields and lists examples, and clarifies 'max_concurrency' default. This greatly exceeds the minimal 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 runs multiple Claude agents in parallel with independent configs. It distinguishes from siblings like 'chain' or 'map' through the parallel execution aspect, but does not explicitly contrast with similar tools.

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 tasks with custom configs but does not provide explicit guidance on when to use this tool versus alternatives like 'map' or 'race'. No when-not-to-use or preconditions are mentioned.

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