select_option

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that fill_field is ineffective here and ranks value as the most reliable matching strategy, but says nothing about failure behavior when no option matches, whether it waits for the select to populate, or whether it fires change events.

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?

Front-loads the purpose, then the sibling constraint, then the parameter manual — a sensible order with almost no filler. Slight redundancy in defining index both in the matching-strategy list and again under Args.

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 explained, and the description covers the key failure mode plus how to address an option. It omits prerequisites (e.g. that the page/select must already be loaded) and error semantics, which is a modest gap for a 4-parameter browser mutation.

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% and all four parameters are nullable anyOf with no descriptions, so the description must compensate — and it does, defining selector, value (matches the value attribute), label (visible text), and index (zero-based) with an explicit mutually-exclusive instruction. Only minor precision is missing, e.g. behavior when multiple of the three are supplied.

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 ('Choose an option in a <select> dropdown') and explicitly distinguishes itself from the sibling fill_field, which handles other inputs but fails here. An agent can route between fill_field and select_option without opening either schema.

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?

Names the alternative that does not work ('fill_field cannot do this — typing into a <select> does nothing'), which is exactly the misuse an agent would otherwise attempt. It also gives a selection rule ('Pick ONE of value / label / index') but does not say when to prefer each strategy beyond calling value 'most reliable'.

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