Select option

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

With no annotations present, the description carries the full behavioral burden. It usefully discloses that custom controls are opened and the visible option clicked automatically, implying only rendered options are clickable, but it does not say what happens when a value/label/index matches nothing, whether a single <select> can accept multiple selections, whether change events are dispatched for framework-controlled components, or how long it waits for options to load.

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 sentences, no filler, and the core capability is front-loaded before the alternative-tool routing. The dense phrasing of the second clause ('opened and their visible option is clicked automatically') is slightly compressed but still readable.

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?

A 10-parameter, zero-required tool with no annotations and no output schema needs more from the description than it gives. Selection semantics are covered, but the targeting model (ref vs selector vs tabId/frameId) and the success/failure signal are left entirely to an undocumented schema, which is a substantive gap for an agent deciding how to invoke it.

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% across 10 parameters, so the description must compensate and it only partially does. 'By value, label or index' implies the value/label/index and plural values/labels/indexes families, but ref, selector, tabId and frameId — the parameters that determine which element and which frame is targeted — receive no explanation at all.

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 (choose one or more options) and a specific resource scope (native <select> or visible custom combobox), which separates it from siblings like type and fill_form. It does not explicitly contrast with fill_form, which can also set form field values, so sibling differentiation is partial rather than complete.

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?

Gives a clear positive condition (native select or visible custom combobox) and an explicit escape hatch: use chrome_cursor when the widget has no semantic combobox/listbox role. That is a named alternative with a selecting condition, though no guidance is given for other ambiguous cases such as a select inside an iframe or a control whose options are not yet rendered.

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