echopath_start_task

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

With no annotations, the description carries the full burden and does deliver real behavioral context: the call returns immediately with a task ID (non-blocking), desktop control is a prerequisite that must be explicitly enabled, and a replay may halt at status 'awaiting_native' requiring an out-of-band subgoal completion. It omits what happens if desktop control is requested without being enabled and the meaning of the vm vs local target distinction.

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?

Front-loaded with the core action and return behavior, then two short routing sentences, then the handoff edge case. No filler, though the handoff paragraph is slightly dense and could be split for readability.

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?

An output schema exists, so return values need not be explained, and the description covers the async nature, the control prerequisite, and the handoff exception. Remaining gaps are the task string format and vm_endpoint semantics, plus no guidance on how this relates to echopath_run_task.

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% across 5 parameters, so the description must compensate. It explains the intent of 'target' (local or VM), 'allow_native_handoff' (permits the awaiting_native stop), and implies 'allow_desktop_control' via the desktop-control prerequisite, but 'task' and 'vm_endpoint' are left entirely undefined in both schema and description.

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 specific verb and resource ('Start a tracked local or VM task') and captures the defining trait of the tool: it returns immediately with a task ID, i.e. it is asynchronous. It does not explicitly contrast with the sibling echopath_run_task, which is presumably the synchronous alternative, so sibling differentiation is only partial.

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?

Explicitly routes the agent for the follow-up phase ('Use echopath_list_runs or echopath_control_run to follow and control it') and describes the handoff path back to echopath_resume_task. It does not say when to prefer this over echopath_run_task or echopath_resume_task directly, but the named alternatives cover the main usage context.

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