agy_run_task

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose that the agent 'operates autonomously with full tool access (file editing, terminal commands, web search, subagents)', which implies potential file modifications and side effects. However, it doesn't explicitly warn about destructive actions, irreversibility, or that the workspace may be altered, and it doesn't mention timeouts or permission implications beyond the schema. This is adequate but not comprehensive.

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 concise, only two sentences, and front-loads the core purpose. It avoids redundancy and is easy to scan. However, it could be slightly more informative without being verbose, but the structure is effective for a quick read.

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 9 parameters, no output schema, and no annotations, the description is too sparse to be fully contextual. It doesn't explain what the tool returns (e.g., success/failure, diff, summary), doesn't clarify the distinction between 'accept-edits' and 'plan' modes, and provides no guidance on when to use this vs. agy_ask or agy_plan. The description covers only the high-level delegation concept, leaving critical operational details to the schema.

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 100%, so all parameters (mode, model, effort, prompt, add_dirs, workspace_dir, conversation_id, timeout_seconds, dangerously_skip_permissions) have their own descriptions. The tool description adds no extra meaning to any parameter—it doesn't elaborate on how to choose mode, what models are available, or how to use add_dirs. With high schema coverage, the baseline of 3 is appropriate.

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's purpose: to delegate a software engineering task (bug fix, refactoring, feature implementation) to Antigravity. The verb 'Delegate' and specific resource types make it unambiguous. However, it doesn't explicitly contrast with sibling tools like agy_plan or agy_ask, so some differentiation is implied but not stated.

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 no guidance on when to use this tool versus alternatives such as agy_plan, agy_ask, or delegate_task. It doesn't mention that planning should use agy_plan or that simple questions should use agy_ask. There is no when-not guidance, leaving the agent to infer usage context from the schema and sibling names.

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