wb_type

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

With no annotations, the description carries the load and does disclose two real traits: it appends at the caret rather than overwriting, and it performs no verification of success. It omits whether focus is required, what happens on hidden tabs, and whether CDP failure surfaces as an error or silence.

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 short clauses, the core behavior front-loaded, and the verification caveat placed as a compact imperative. Nothing 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?

For a 6-parameter tool with a nested target object, no annotations, and no output schema, the description is too thin. The selector/target duality, session scoping, and the ambiguous inputMode semantics — the places an agent will actually get it wrong — are all unaddressed.

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 50%, so the description needed to compensate and does not. 'The target's caret' vaguely gestures at the target object, but the legacy selector-vs-target choice, session override, timeoutMs, and inputMode's applicability to typing are all unexplained (the inputMode description in the schema actually discusses click/check, muddying whether 'dom' is valid here).

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 effect: insert text at the target's caret, explicitly not replacing existing text, delivered via CDP. That non-replacing qualifier is what separates it from wb_fill, though the sibling is never named outright.

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?

No statement of when to pick this over wb_fill or wb_press_key, and no prerequisites (does the element need focus first? does it work in hidden tabs?). The trailing 'Verify the result separately' hints at a follow-up call but gives no condition or named alternative.

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