start_edit

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

The description discloses important behavioral traits beyond the annotations: the operation is asynchronous, runs in an isolated Git worktree, and cannot directly alter the active checkout. This gives an agent a clear picture of side effects and scope, adding value over the basic readOnlyHint/destructiveHint flags. It does not detail post-completion behavior, but the core safety and execution model is well covered.

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 sentences with zero waste. The primary action is front-loaded, and the key constraint ('cannot directly alter the active checkout') is stated immediately. Every clause adds value.

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?

For a tool with 9 parameters and no output schema, the description covers the essential behavioral context (async, isolated, non-destructive to active checkout) but omits what the caller receives in return (e.g., a run ID) or how to track progress. Since it is an async starter, this is a meaningful gap. However, the schema covers parameter details, so the description is not fully inadequate.

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 89%, so the input schema already documents nearly all parameters (cwd, task, model, effort, context, max_retries, model_policy, acceptance_criteria; timeout_minutes lacks a description but is covered by min/max). The description adds no parameter-specific meaning beyond what the schema provides, so 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 verb ('Start'), the resource ('Antigravity implementation worker'), and a key distinguishing constraint ('in an isolated Git worktree', 'cannot directly alter the active checkout'). This separates it from sibling tools like start_analysis or start_review, which serve different purposes, and from apply_run that would directly modify the checkout.

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 conveys the intended use (starting an implementation worker in isolation) but does not explicitly state when to use it versus alternatives, nor provide exclusions. The isolation constraint hints at when not to use it (when direct checkout modification is needed), but this is not made explicit. No alternatives are named.

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