start_review

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

Annotations already declare readOnlyHint and destructiveHint, so the safety profile is known. The description adds value by specifying it is 'asynchronous' and a 'worker', which implies background execution and potential delays. It also names the action as 'critically review', but does not mention how results are returned or how to monitor progress. Given the high annotation coverage, the additional async context earns a 4.

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, focused sentence that front-loads the core action and purpose. It avoids redundancy with the schema and annotations, containing only information that an agent cannot derive elsewhere. Every word earn its place.

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 and no output schema, the description should clarify the operational flow. It mentions 'asynchronous' but does not state how the agent will receive results (e.g., a run ID, use get_run). The sibling tools like get_run and list_runs imply the pattern, but the description could be more explicit. However, the schema covers parameter details well, so a 3 is appropriate for a moderately complex tool.

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 most parameters already have detailed descriptions in the schema. The tool description itself adds almost no parameter-specific information beyond the general purpose. This meets the baseline of 3 for high coverage, but does not go beyond to clarify parameter relationships or usage nuances.

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 states a specific verb ('Start'), a specific resource ('Antigravity worker'), and a clear purpose ('critically review code or a proposed change'). This distinguishes it from sibling tools like start_media_analysis or start_image_generation, which target different domains. The phrase 'read-only' also adds a safety signal.

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 clearly implies it is for code review tasks, which separates it from media/image/analysis tools. However, it does not explicitly mention alternatives or conditions for when to use this instead of other 'start_*' tools like start_analysis or start_edit. Since the domain is highlighted, it provides clear context without exclusions.

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