Skip to main content
Glama
Sign In
agentgo-mcp

agentgo-mcp

by Moha2005269
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

browser_act

Perform real browser clicks, typing, selections, and uploads on elements by ref; wait for the page to settle and return only the changed state for the next step.

Instructions

Act on an element by ref with real input, wait for the page to settle, and get back only what changed. action: click, fill (text), press (key), check, uncheck, select (value, or values for a multiple list), hover, scroll (to: top|bottom, or ref; until: a text to scroll to, in the page or ref's list), type (text at focus), upload (paths). Add submit:true to fill to press Enter; expect {gone, shows, enabled, url, changes} must hold after, or it fails. If the reply is approval.required or handoff.required, call browser_wait_human.

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": {
      "action": "<action>"
    },
    "name": "browser_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNo
keyNoe.g. Enter, Tab, Escape, ArrowDown, a
refNo
textNo
pathsNo
untilNo
valueNo
actionYes
expectNo
submitNo
valuesNoselect: several options of a multiple list
approvalIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.6
    • addedInput schema / properties / expect
      Added value: +{
+  "type": "object"
+}
    • addedInput schema / properties / until
      Added value: +{
+  "type": "string"
+}
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the settle-then-diff return semantics ('get back only what changed'), the failure mode ('expect ... must hold after, or it fails'), and the human-approval handoff. It does not describe what happens to page state on failure or whether actions are retried/atomic, leaving some mutation risk unstated.

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 the core contract before the dense action-by-action parenthetical, and every clause maps to a real parameter or behavior. The long run-on action list is information-dense but sacrifices scanability, which keeps it from a 5.

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 12-parameter mutation tool with a nested 'expect' object, no annotations and no output schema, the description covers the action vocabulary, the key modifiers, the assertion failure mode, and the return shape ('only what changed'). An agent can call it without opening sibling tools.

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 description coverage is only 17%, so the description must compensate and largely does, binding each action to its parameters: fill→text, press→key, select→value/values, scroll→to/until/ref, type→text, upload→paths, plus submit and expect semantics. Gaps remain: 'ref' is only implied by 'act on an element by ref' rather than defined, and approvalId is never mentioned.

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?

States a specific verb and resource ('act on an element by ref with real input'), plus the post-condition ('wait for the page to settle') and the return contract ('only what changed'). The enumerated action list makes it immediately distinguishable from browser_read, browser_wait and browser_batch.

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

Usage Guidelines4/5

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

Gives per-action routing ('click, fill (text), press (key)...'), explains modifiers ('Add submit:true to fill to press Enter') and names the escalation path ('If the reply is approval.required or handoff.required, call browser_wait_human'). It stops short of saying when NOT to use this tool versus browser_batch or browser_read, so no explicit exclusion.

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

Deploy Server

Other Tools