Split a task into chunks and distribute them across parallel workers to process work concurrently.
Split task into chunks and process in parallel
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Task description. | |
| chunks | Yes | Task chunks to assign across workers. | |
| workers | No | Number of parallel workers to plan. |
Changes observed during successful MCP inspections.
v0.1.0-alpha.29Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, and it delivers only a one-line mechanism. It says nothing about side effects, whether workers are real concurrency or just a planning hint, failure/partial-completion behavior, or result aggregation.
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?
A single short sentence with no wasted words and the core action front-loaded. It is concise, but the brevity comes at the cost of under-specification rather than disciplined economy.
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?
A parallel fan-out tool with no annotations, no output schema, and only a one-line description leaves critical questions unanswered: what gets returned, whether the split is automatic or manual, and how workers interact with the chunks. The description is too thin for the tool's apparent 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 coverage is 100%, so task, chunks, and workers are already documented in the schema. The description restates the chunking concept but adds no syntax, format, or constraint detail (e.g., chunk-to-worker mapping), so the baseline 3 applies.
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?
States a verb-and-resource action (split a task and process chunks in parallel), which is clearer than a tautology. However, it gives no differentiation from the sibling swarm tools (hb_swarm_consensus, hb_swarm_hierarchy, hb_swarm_stigmergy), so an agent cannot tell when this parallel primitive is the right choice.
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?
No when-to-use, when-not-to-use, or alternative-selection guidance is present. The agent must infer the context entirely from the name and the sibling list, which is exactly the situation the guidelines dimension is meant to penalize.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.