agy_run_start

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

With no annotations, the description carries the behavioral burden and does disclose key non-obvious behavior: foreground vs. persistent sessions, bridge-owned tasks, and that --dangerously-skip-permissions is always forwarded. It does not discuss failure modes or resource side effects, but the important behavioral constraints are present.

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 compact sentences, each carrying distinct information with no filler. The purpose is front-loaded and the mode details, sibling pointer, and permission constraint are separated logically.

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 9-parameter surface and no annotations, the description covers the main behavioral choices and the key exclusion. It does not connect to the run lifecycle siblings (e.g., agy_run_wait/result) or clarify workspace prerequisites, so a small completeness gap remains.

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 coverage is 0%, yet the description explains the three least obvious parameters: mode values, conversation continuation semantics, and the required dangerously_skip_permissions flag. Several other parameters (model, sandbox, timeout_seconds, additional_directories) are left to inference from their names, so the 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 first sentence names a specific action (start or continue) and resource (one foreground Antigravity Run), and the mode breakdown adds precision. It also names the sibling for artifact-producing tasks, so the agent can distinguish it from agy_start_with_expected_file.

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?

It explicitly tells the agent when to use the alternative ('reviews and other artifact-producing tasks') and when to be cautious (interactive mode sparingly). It also explains how conversation_id continues an existing conversation, which guides invocation.

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