Skip to main content
Glama

Select option

browser_select
Destructive

Select a value on a . Required: sessionId, observationId, elementId, value. value must match an or a unique option label. A non-select element returns WRONG_ELEMENT_TYPE with the actual tag and role. Unknown values return INVALID_SELECT_VALUE and do not change the select. A disabled option, including a placeholder such as Please select an option, returns OPTION_DISABLED and does not change the select. A failure before the page changes keeps the observation valid. STALE_OBSERVATION means observe again and retry. On a sensitive site, select returns APPROVAL_REQUIRED with approvalId and does not change the control until Approve. Approve runs that select once. The completed success includes that same approvalId and approved: true. A select that did not need approval does not include approvalId. After Deny, the next select of that value returns APPROVAL_DENIED with that approvalId once, even when the observation id and element id changed. A different value asks for a new approval. A later select of the same value may ask again. While it is still pending, the same element and value returns APPROVAL_PENDING.

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": {
      "sessionId": "<sessionId>",
      "observationId": "<observationId>",
      "elementId": "<elementId>",
      "value": "<value>"
    },
    "name": "browser_select"
  }
}

Input Schema

NameRequiredDescriptionDefault
valueYes
elementIdYes
sessionIdYes
observationIdYes
idempotencyKeyNoA key replays the original result only within ~60 seconds of the first call, only for the same Mcp-Session-Id, the same credential (API key or OAuth token), the same browser session, and the same tool. After the window, or under a different session/credential/tool, the call executes and bills normally. Reusing a key with different arguments returns IDEMPOTENCY_KEY_REUSED and is not executed or billed. Refusals (e.g. NO_HISTORY_ENTRY) are not cached, so the same key re-executes once state changes. A key passed in _meta is ignored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes far beyond the annotations, which only say it is destructive/non-idempotent/open-world. It enumerates concrete error codes (WRONG_ELEMENT_TYPE, INVALID_SELECT_VALUE, OPTION_DISABLED, STALE_OBSERVATION), states that failures leave the observation valid, and fully documents the approval lifecycle including re-request and denial behavior. That is exactly the mutation-specific context annotations cannot carry.

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

Conciseness4/5

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

Front-loaded with purpose and mostly dense with earned content, but it is a single long paragraph with some repetition ('does not change the select' recurs) and the 'Required: ...' clause merely restates the schema. Slightly heavy toward approval minutiae, but still readable and largely justified.

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

Completeness4/5

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

For a destructive, open-world tool with no output schema, the description covers error taxonomy, observation-validity implications, and the approval flow in enough depth to call it correctly. It omits idempotencyKey semantics (deferred to the schema) and the return shape beyond approvalId/approved, but those are minor gaps.

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

Parameters3/5

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

Schema coverage is only 20%, so the description must compensate and it partly does: it explains that 'value must match an <option value> or a unique option label', which is the parameter most likely to be misused. However, sessionId, observationId and elementId get no semantic explanation beyond restating that they are required, leaving the coverage gap only half filled.

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 opening 'Select a value on a <select>' is a precise verb+resource and immediately distinguishes this from click/type siblings. It also states the required parameters in the same breath, so the agent knows exactly what this tool does without inspecting the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The description implies usage (act on a select element, be prepared to re-observe on STALE_OBSERVATION) but never explicitly says when to choose this over browser_click or keyboard input, nor does it state the prerequisite that an observation must exist first. Guidance is inferable but not spelled out.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.