delegate_task

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

With no annotations, behavioral transparency is carried by the prose; it does disclose worktree isolation, default agent auto-selection, post-run checks, and memory-project behavior. It does not explain the write flag, background behavior, or side effects/cost of delegation, leaving important execution behavior undisclosed.

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 front-loaded with a clear purpose and each sentence adds a distinct piece of parameter/behavior guidance with little fluff. It is dense and somewhat wall-of-text, but the complexity of 14 parameters justifies the length.

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 complex tool with 14 parameters, no annotations, and zero schema property descriptions, this description is incomplete: it leaves the task prompt, write mode, effort, model, and background behavior unexplained. An agent could call the tool but would likely need external knowledge to use those parameters correctly.

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 0% for 14 parameters, so the description must compensate. It explains agent, required_capabilities, exclude_agents, worktree, checks, memory_project, and cwd context, but omits core parameters like prompt, write, effort, model, agent_name, and background—prompt is especially important since it is the task payload.

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 opening line states a specific action ('Delegate a task') and target ('headless CLI agent or role'), so an agent can tell what the tool is for. It does not explicitly distinguish itself from siblings like route_task, but the delegated-vs-routed distinction is reasonably inferable.

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 conditional guidance for parameters ('Pass required_capabilities when...', 'exclude_agents to keep...') and mentions job_review for consuming checks. It does not say when to choose delegate_task over route_task or other siblings, so usage context is helpful but not alternative-focused.

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