Run Antigravity task

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=true, so the safety profile is covered. The description still adds real value beyond them by disclosing the sandboxing mechanism (copies into a temp dir, runs agy --sandbox), the includePaths narrowing behavior, and the taskId return token. The 'source is unchanged' claim sits in mild tension with destructiveHint=true but is not a direct contradiction, since the destruction happens inside the sandbox/task state rather than the source tree.

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?

Three tight sentences, front-loaded with the mechanism (copy to temp dir and run in sandbox), then the includePaths qualifier, then the return/immutability note. No filler and no repetition of the title.

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, but for a 10-parameter tool with 0% schema description coverage the description covers only one parameter and no workflow positioning. An agent can call it with the two required params but has no basis for choosing mode, role, isolateWorktree, timeoutSeconds, or how to build acceptanceCriteria.

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% and there are 10 parameters, so the schema provides names and types but no semantics. The description only explains includePaths ('narrows copied files or folders'), leaving mode, role, model, sessionId, timeoutSeconds, isolateWorktree, workingDirectory, and the whole acceptanceCriteria structure undocumented in prose. That is far too thin to compensate for a 0% coverage schema.

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 gives a concrete verb+resource ('Copy non-ignored project files to a temporary directory and run agy --sandbox there') and states the returned handle (taskId). It clearly separates this from read-only siblings like antigravity_preview/antigravity_status, though it never names a specific sibling to disambiguate from antigravity_resume or antigravity_integrate.

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?

There is no explicit when-to-use guidance: nothing says this starts a new task versus sitting alongside antigravity_resume, antigravity_cancel, or antigravity_verify. The phrase 'Returns a taskId' hints that this is the entry point, but the agent must infer that. No exclusions or prerequisites are given.

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