start_task

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

Despite no annotations, the description discloses key behavioral traits: no subprocesses launched, read-only for review/investigate, returns machine-readable next_action, profile, warnings, etc. It explains mode-specific behavior but does not mention potential state changes or side effects for the implement mode.

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 structured with a lead sentence followed by mode-specific bullets and a summary of return values. It is informative without excessive verbosity, though some terms like 'host_spawn_waves' may require domain knowledge.

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 three modes and no output schema, the description covers purpose, mode behavior, return values, and constraints (no subprocesses). It lacks error handling or detailed output format definitions but is sufficient for agent comprehension.

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% with parameter descriptions already present. The description adds value by explaining the implication of each mode (the enum parameter) and the return structure, and clarifies that workspace_root is an alias for cwd, going beyond schema alone.

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 'Start a host-native task handoff' with three distinct modes (implement, review, investigate), effectively distinguishing it from sibling tools like plan_task or route_task which serve different purposes. Each mode's specific behavior is explicitly described.

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 provides clear guidance for each mode's intended use (implement for simple/complex tasks, review for read-only, investigate for profiling). It implies when not to use it by stating 'no provider subprocesses launched,' but lacks explicit alternatives or when-not conditions.

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