Skip to main content
Glama

Select dropdown option by ref

browser_select

Chooses an option in a native dropdown using a page element reference, with case-insensitive label matching and substring fallback; returns status and page details.

Instructions

Choose an option in a native dropdown by ref (from browser_observe / browser_find). Free — no model call. The option label is matched case-insensitively, then by substring. For custom (non-native) dropdowns, click the control with browser_click, then click the revealed option. Returns {ok, detail, page}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ref": "<ref>",
      "option": "<option>"
    },
    "name": "browser_select"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYesRef of the <select> element.
optionYesOption label to choose.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does a solid job: it discloses cost ('Free — no model call'), the matching algorithm ('case-insensitively, then by substring'), and the return shape {ok, detail, page}. It stops short of saying what happens when no option matches (error vs. ok:false) or whether the call waits for the menu to settle.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the action and scope, then the alternative path, then the return shape. Nothing is redundant with the title or schema, and every clause carries actionable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter, non-destructive interaction tool with full schema coverage and no output schema, the definition covers ref provenance, matching semantics, the escape hatch to browser_click, and the return envelope. Only the failure/no-match case is unstated, which is minor at this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning beyond the schema: 'ref' is qualified as coming from browser_observe / browser_find, and 'option' is specified as a label matched case-insensitively and then by substring. That matching rule is behavior an agent cannot infer from the bare schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Choose an option in a native <select> dropdown') and narrows the scope with 'native', which immediately separates it from the sibling browser_click path used for custom dropdowns. An agent can pick between them 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.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states both when to use it (native <select>) and when not to, naming the alternative workflow explicitly: 'For custom (non-native) dropdowns, click the control with browser_click, then click the revealed option.' It also tells the agent where the ref comes from (browser_observe / browser_find), so the prerequisite step is clear.

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