handoff

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

Beyond the openWorldHint/readOnlyHint=false annotations, it discloses the mechanics precisely: a window opens on the user's screen, the call effectively blocks until they close it, and fresh cookies are returned to the session. That is exactly the kind of state-change and blocking behavior an agent needs before invoking a mutating, human-in-the-loop tool.

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?

Three short sentences, front-loaded with the core action, then the when-to-use examples, then the mechanism and the required follow-up call. Nothing is redundant.

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?

An output schema exists, so return values need no explanation, and the description covers the interaction model and the mandatory snapshot follow-up well. The unexplained 'reason' parameter remains a small but real gap for a tool at this complexity.

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 description must carry parameter meaning, and it does not: neither session_id nor reason is mentioned or explained anywhere in the text. Only an indirect inference from 'this session' hints at session_id.

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 (hand the current page over to the user in a visible window) with concrete triggering cases: CAPTCHAs, 2FA prompts, expired logins. An agent can distinguish this from automation siblings like click/type_text because it explicitly delegates control to a human.

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?

It gives clear when-to-use criteria ('anything you shouldn't or can't do') and even prescribes the follow-up step ('Then call snapshot'). It never contrasts with the login siblings (start_login/complete_login), which is the main gap for a handoff-vs-automated-login decision.

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