agy_interactive_start

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

With no annotations provided, the description carries full burden. It discloses behavioral traits: bridge queues input, depends on transcript semantics, may deadlock if response event types change, completed responses do not terminate session, and clarifies that sandbox/additional_directories are CLI policy hints not security boundaries.

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 two paragraphs, concise for the complexity, front-loaded with experimental label and purpose. Each sentence adds value, though some details could be more streamlined.

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 complexity (7 params, experimental, interactive session) and existence of output schema (so return values not needed), the description covers purpose, usage, behavioral notes, and some parameter info. It lacks explicit mention of blocking behavior or return format, but output schema handles that.

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%, so description must compensate. It adds meaning for 'sandbox' and 'additional_directories' by explaining they are policy hints, not containment. However, other parameters like timeout_seconds and dangerously_skip_permissions are not explained, so compensation is partial.

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 clearly states 'start a persistent interactive Antigravity session', specifying a specific verb and resource. It distinguishes from siblings by noting that agy_target_send_text is used for subsequent prompts and agy_cancel to close the session, making the purpose clear.

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 explicitly advises 'This should not be used often', mentions alternatives (agy_target_send_text for subsequent prompts, agy_cancel to close it), and warns about potential deadlock, providing clear when-to-use and when-not-to-use guidance.

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