Run general-purpose Antigravity sub-agent 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 so well: it discloses synchronous blocking, the auto-DENY behavior for gated tool requests and where denials surface (denied_actions), that this server never edits settings.json, that edit_scope is audit-and-replay rather than a sandbox, and that auto_approve is the --dangerously-skip-permissions switch. These are non-obvious side effects an agent must know before calling.

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 purpose and the synchronous contract, then defaults, then the permission/audit caveats. Dense with little waste, though the auto_approve and sandbox guidance is partly restated and the single long paragraph mixes return-value description with operational warnings.

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?

There is no output schema, and the description compensates by enumerating what the result carries (final response, conversation_id, token usage, denied_actions, files_touched/scope_violations audit when cwd is a git repo). Combined with the timeout/idle-kill semantics in the schema, an agent has enough to call and interpret this 12-parameter tool 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 100%, so the baseline is 3, but the description adds real meaning beyond the schema for edit_scope ('audit-and-replay control, not a sandbox — the CLI writes files itself') and auto_approve ('expert full-auto switch ... pair it with sandbox'). It also states defaults (mode accept-edits, effort medium) that the schema does not.

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?

Specific verb + resource: 'Delegate a general-purpose coding task to the Antigravity (agy) CLI and block until the headless run exits.' The parenthetical '(synchronous; the tool call IS the wait)' immediately separates it from async siblings like watch_task, so an agent can route without opening schemas.

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?

Gives concrete operational context: headless runs auto-deny prompting tools, permission must be pre-granted by the user via permissions.allow, file edits inside cwd never prompt, and auto_approve should be paired with sandbox. However, it never names the sibling alternative (explore_task) or states when this blocking tool is preferred over the watch/explore pattern, leaving that inference to the agent.

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