start_analysis

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

Annotations already provide readOnlyHint=true and destructiveHint=false, covering safety. The description reinforces 'read-only' and adds 'asynchronous' and 'bounded', which are useful behavioral traits not in annotations. However, it does not disclose what the worker returns (e.g., a run ID), how to retrieve results, or whether the process is cancellable—information an agent needs for an async tool. It adds some context but not enough for 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 sentence with zero filler. It front-loads the core action and purpose, and every word earns its place. It is appropriately sized for a tool whose schema and annotations carry the detailed parameter and safety information.

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, no output schema, and an asynchronous nature, the description is notably incomplete. It does not mention what the tool returns (e.g., a run ID), how to track progress (e.g., via get_run or list_runs), or any prerequisites. The agent is left to infer the workflow from sibling tool names. Given the complexity, more guidance is expected.

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 clear descriptions. The tool description adds no parameter-specific semantics—it does not mention cwd, task, model, effort, or any other parameter. Per the rubric, a high coverage baseline of 3 is appropriate, and the description does not compensate with additional clarification.

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 action ('Start an asynchronous read-only Antigravity worker') and its purpose ('bounded investigation or planning'). The verb+resource are clear, and the mention of 'read-only' distinguishes it from mutation tools. However, it does not differentiate from sibling tools like start_media_analysis or start_review, which also start workers; the name 'analysis' implies generality but is not explicitly contrasted.

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 gives a clear context for when to use it ('for bounded investigation or planning') which implies a scope, but it does not state when not to use it or mention alternatives. With many sibling start_* tools, explicit routing guidance (e.g., 'use start_media_analysis for media-specific tasks') is missing, leaving the agent to infer based on the name.

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