browser_resume

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

No annotations exist, so the description carries the full burden. It does disclose one genuinely useful behavioral trait — approval is scoped to a single pending irreversible action — but omits what happens on an expired session, whether resumption is idempotent, and what happens to values already supplied.

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?

Two tight sentences, front-loaded with the continuation purpose. The scoping clause about approval earns its place by disambiguating a risky operation, though the enjambed sentence mixes three separate modes.

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 not be described, but for a 6-parameter continuation tool with nested objects, no annotations, and low schema coverage the description leaves gaps on allowed_domains semantics, secret resolution, and failure modes.

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 only 17%, with just 'session' documented. The description partially compensates by mapping to concepts (values, goal update, approval, irreversible action), but 'allowed_domains', the secret_ref/origins wrapper, and 'dialog.value_key' are never explained, leaving half the parameters opaque.

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+resource ('Continue an existing session after a handoff') and enumerates the concrete modes: supplying values, refining the goal, or approving one pending irreversible action. This implicitly separates it from browser_run (which starts a session) and browser_act, though it never names a sibling explicitly.

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 phrase 'after a handoff' supplies a clear triggering condition, and the three listed activities describe when each capability applies. It stops short of stating exclusions or naming an alternative tool to use instead when no handoff has occurred.

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