ask-antigravity

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

With no annotations, the description fully carries the behavioral disclosure burden. It reveals that the agent has file tools, that workspace grants read+write access, that prompt_file wins over prompt, that cleanup deletes the prompt/system files, and that save_artifact always writes an artifact. These are meaningful behavioral traits that directly inform safe invocation.

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?

The description is front-loaded with a one-sentence purpose, followed by a brief behavior paragraph and a clean parameter list. Every line adds operational value with no filler, making it appropriately sized for an 11-parameter tool.

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?

Given the tool's complexityed—11 parameters, file-wielding agent, potential workspace modifications—the description covers defaults, workspace semantics, resume mechanics, cleanup, artifact saving, and model options. Since an output schema exists, return-value details are unnecessary. Nothing critical is missing for an agent to invoke it 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 0%, but the description supplies a semantic gloss for every single parameter, including precedence rules, special values like workspace='none', default behaviors, and side effects. This fully compensates for the schema's lack of descriptions.

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 opens with a specific verb and resource: 'Ask the Google Antigravity AGENT (Gemini 3.8 Flash / Pro)' and clearly characterizes it as a coding agent with Read/Write/Bash tools, comparable to Claude Code or Codex. This makes the tool's identity and scope immediately distinguishable from a generic ask-gemini sibling.

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?

The description gives clear context for when to use the tool: 'By default it works in the current directory... so it can read and run your repo like Codex,' and highlights distinguishing features like parallel swarm execution and one-click resume. It stops short of explicitly naming alternatives or when not to use it, so it lacks full exclusionary routing.

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