browser_ask_user

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds the human-handoff model, but does not say whether the call blocks until the user responds, whether it returns a status immediately, or what happens on timeout – the key behavioral questions for a handoff 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?

One sentence, front-loaded with the core action and then the enumerated cases. No redundant restatement of the name or schema.

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?

With no output schema and no annotations about interaction semantics, the description should say what the agent gets back and whether it waits – a real gap for a tool whose whole purpose is a blocking-style handoff. It is otherwise sufficient for a 3-parameter 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?

The schema leaves the 'reason' enum values undocumented; the description supplies meaning for three of them (human_check=CAPTCHA, trusted_input=ignored clicks, other=choose), which is genuine value beyond the schema. tab_id's default and message's purpose are already covered by schema descriptions.

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?

States a specific verb and resource ('Ask the user') plus the exact class of situations it exists for (sign in, CAPTCHA, unclickable control, free choice). That framing is distinct from every sibling, which are browser-automation actions.

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 enumerated reasons implicitly define when to call it – when the agent cannot complete the step itself – and 'do what you cannot' sets the condition. It stops short of stating when NOT to use it (e.g. prefer retry/navigate first) or what to do after the user acts.

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