ask

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

With no annotations, the description carries the burden well: it discloses the side effects (tab focus, panel, target highlighting, desktop notification) and that the call blocks until the user acts. It also explains the semantic of a 'cancelled' result. It stops short of describing what happens when the timeout expires or how the user's answer is returned.

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?

Five tight sentences, front-loaded with the core behavior, then trigger conditions, then the cancellation contract. No filler, and the most decision-relevant rule (stop on 'cancelled') is last for emphasis without burying the purpose.

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 an 8-parameter blocking tool with a nested object and no output schema, the description covers purpose, triggers, side effects, and result semantics adequately. The remaining gap is timeout-expiry behavior and how the user's response surfaces to the agent.

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 100%, so the schema already documents all eight parameters thoroughly, including the nested 'until' object and target refs. The description adds only light reinforcement ('highlights your targets'), which is the baseline expectation when the schema does the heavy lifting.

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 action (hand control to the user for one step, then resume) with a unique verb-resource pairing that no sibling tool shares. An agent can immediately tell this is the human-in-the-loop pause tool and not a retry/wait/act mechanism.

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?

Explicit when-to-use triggers are enumerated (captcha, QR login, SMS/OTP, human confirmation) plus a positive routing rule: 'Use it instead of retrying a step that needs a human.' It also defines the terminal case ('cancelled' means the user said no: stop the task, do not look for another way), which is when-not guidance no sibling provides.

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