antigravity_ask

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

With no annotations, the description carries the full burden, and it does disclose useful traits: async execution, a returned task ID, isolation in a fresh scratch directory, limited context, and untrusted external output. It stops short of permissions, timeouts, or whether the source directory can be mutated (relevant given allowSnapshotWrites).

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?

Terse, front-loaded fragments with no filler; the async/return fact leads and the safety note closes. Efficient for the amount of information conveyed.

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 an 8-parameter tool with low schema coverage and no annotations or output schema, the description is too thin: it omits most parameter meanings, any timing/timeout expectations, and how the eventual result is retrieved beyond a bare pointer to polling.

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 only 25% across 8 parameters, so the description should compensate. It hints at contextFiles ('selected context only') and cwd isolation ('fresh scratch directory'), but leaves base, mode, model, and timeoutMs unexplained, so most parameters remain undocumented.

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 clear verb+resource ('Start ask asynchronously') and adds scope detail ('fresh scratch directory; selected context only') and a return value ('returns task ID'). However, it does not distinguish this from close siblings like antigravity_delegate or antigravity_review, leaving the agent to infer which one to pick.

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?

'Poll status then result' implies a follow-up workflow using the sibling antigravity_status/antigravity_result tools, which is helpful. But it never states when to choose this tool versus delegate/review, nor any preconditions or exclusions.

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