agy_run_start

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It reveals that the tool runs in the foreground, supports two modes, and requires dangerously_skip_permissions. However, it lacks details on side effects, resource creation, blocking behavior, or what happens after invocation (e.g., whether it returns immediately or waits).

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 a single paragraph with three sentences, no wasted words. It front-loads the main purpose and then details key parameters. It is concise but could benefit from bullet points or clearer separation of mode behavior.

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 has 9 parameters (2 required), no schema descriptions, and an output schema, the description is not fully complete. It covers key concepts but omits important context like whether the run is synchronous, how to handle timeouts, and the meaning of optional parameters like sandbox. The output schema exists but the description does not hint at the return shape.

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?

The input schema has 0% description coverage, so the description must compensate. It explains 'mode', 'conversation_id', and 'dangerously_skip_permissions' but leaves 'prompt', 'workspace', 'timeout_seconds', 'model', 'sandbox', and 'additional_directories' unexplained. This partial coverage is adequate but incomplete.

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 the tool starts or continues a foreground Antigravity Run, with verbs 'start' and 'continue'. It distinguishes between modes ('task' vs. 'interactive') and mentions continuing via conversation_id. The purpose is unambiguous and distinguishable from sibling tools like agy_run_cancel or agy_run_wait.

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 provides specific guidance on when to use each mode: 'task' for normal tasks and 'interactive' for persistent conversations 'sparingly'. It also notes that dangerously_skip_permissions must be true. However, it does not explicitly state when not to use this tool versus other run-related siblings.

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