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

The description adds meaningful behavior beyond the annotations: the session is fresh and ephemeral, it may use Browserbase or a mock, and it returns liveViewUrl rather than purchaser email. Since annotations already signal non-readonly, non-idempotent, non-destructive behavior, the description covers the remaining important traits well, though it does not mention how sessions relate to an existing live session.

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 no wasted words. The most important constraint ('ASSISTED mode only') is front-loaded, followed by the core behavior and the key alternative routing.

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 low-complexity, single-parameter tool with an output schema and full parameter documentation, the description is complete. It covers mode restriction, session type, return value, and the relevant sibling alternative, so an agent has what it needs to call it correctly.

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 coverage is 100% and the single optional 'reason' parameter already has a clear description and example in the schema. The tool description adds no additional parameter-level meaning, so the schema carries the burden and the baseline score applies.

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 uses a specific verb ('Start') and resource ('fresh ephemeral Browserbase (or mock) co-pilot session'), and clearly states that it returns liveViewUrl with no purchaser email. It also distinguishes itself from get_self_serve_portal, so an agent can differentiate without inspecting sibling tools.

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?

'ASSISTED mode only' is an explicit precondition, and the description names the alternative ('get_self_serve_portal') for when the Owner prefers their own browser. This leaves no ambiguity about when this tool is appropriate.

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