create_chrome_instance

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

No annotations are provided, so the description carries the full burden. It discloses that a session_id (UUID) is returned, which is useful behavioral context. However, it lacks critical details: whether this consumes significant resources, if there are rate limits on instance creation, what happens if too many instances are open, or if it requires specific permissions. For a tool that likely launches a browser process, this is a significant gap in transparency.

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, efficient sentence that front-loads the core action ('Create a new Chrome browser instance') and key outcome ('return session_id'). There is zero waste—every word contributes essential information without redundancy or fluff.

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 complexity (creating a browser instance), no annotations, and an output schema (which likely covers the session_id return), the description is minimally complete. It states the purpose and return value, but lacks context on resource usage, error conditions, or integration with sibling tools. For a tool with potential side effects (launching processes), more behavioral detail would be helpful, but the output schema reduces the burden.

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 0%, so the schema provides no parameter descriptions. The description adds no parameter information beyond what's inferred from the schema (e.g., 'headless' might control headless mode). It doesn't explain what 'headless' means, why viewport dimensions matter, or default behaviors. With 3 parameters and 0% coverage, the description fails to compensate adequately, but it's not misleading, so a baseline 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 action ('Create a new Chrome browser instance') and the resource ('Chrome browser instance'), with the specific outcome of returning a session_id. It distinguishes from siblings like 'get_instance_info' or 'close_instance' by focusing on creation rather than querying or termination. However, it doesn't explicitly differentiate from all siblings (e.g., 'set_browser_config' might also involve browser setup).

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. It doesn't mention prerequisites (e.g., whether an existing instance must be closed first), when not to use it (e.g., for reusing instances), or refer to sibling tools like 'close_all_instances' for cleanup. Usage is implied only by the action of creation.

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