Run tests in the native agy sandbox

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

Annotations already flag destructive/openWorld/non-readOnly, and the description adds substantive context beyond them: asynchronous execution, captured exit status and file fingerprints, optional up to three repair retries, and the absence of Docker/host fallback. That said, it doesn't explain what gets mutated or how expectedSha256 gates execution.

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?

Four tight sentences, front-loaded with the core action and followed by capability, constraint, and routing information. No filler, though the last sentence is somewhat list-like.

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-value explanation isn't required, and the description covers the async workflow and downstream taskId usage. However, for a destructive tool with 0% schema coverage on a mandatory hash parameter, the description leaves meaningful gaps about how taskId and expectedSha256 are obtained and what timeoutSeconds controls.

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 including a nested command object, so the description must compensate and largely does not. It mentions retry behavior (matching the retries max of 3) but says nothing about taskId, expectedSha256, timeoutSeconds, or the command's executable/args shape.

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 an asynchronous continuation that executes a command) plus what it captures, which separates it from siblings like antigravity_run and antigravity_verify. It never explicitly names a sibling to contrast against, so it stops short of a 5.

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 real routing guidance ('Use the returned taskId for events, result, review and integration') and a negative constraint ('No Docker or host execution fallback'), telling the agent when this path is and isn't appropriate. It does not say when to prefer antigravity_run or antigravity_record_test, so no explicit alternative comparison.

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