Skip to main content
Glama

act

Performs browser actions on elements by stable ID—click, fill, select, check, upload, scroll, navigate tabs, handle dialogs, and wait for expected text, URL, or disappearance.

Instructions

Act on id -> status + changes. select: label. tab: list|new:URL|switch:N|close:N; dialog: accept[:TEXT]|dismiss. expect: text|url:X|gone:ID

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": "act"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo
valueNo
actionYes
expectNo
dry_runNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

C2.5/5.0
Behavior2/5

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

The description adds a small amount of behavioral information by mentioning "status + changes" and providing post-action expectation forms. With no annotations, however, it does not explain side effects, dry_run behavior, expectation failures, waiting or timeout behavior, or the effects of tab and dialog operations.

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

Conciseness3/5

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

The description is front-loaded and extremely economical, with no filler. Its compression is excessive in places: it is unclear which grammars belong in value versus expect, and shorthand such as "expect: text|url:X|gone:ID" requires guesswork about literal text and matching semantics.

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

Completeness2/5

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

For a tool with seventeen actions, five undocumented parameters, no annotations, and no output schema, this is only a partial contract. The specialized tab, dialog, and expectation syntax is helpful, but too many common invocation and behavior details remain unspecified.

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?

Despite 0% schema description coverage, the description usefully supplies encodings for select labels, tab subcommands, dialog responses, and expect values. It does not explain dry_run, which actions require id or value, or value formats for common actions such as fill, press, upload, scroll, and wait_for.

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

Purpose3/5

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

"Act on id -> status + changes" identifies a target and a result, but "act" is generic and the description never explicitly establishes the browser/page context. The tab and dialog syntax narrows the purpose somewhat, yet there is no differentiation from siblings such as fill_form or open.

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

Usage Guidelines2/5

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

There is no explicit guidance about when to choose this tool, when not to use it, or which sibling should handle related tasks. It also omits prerequisites such as how to obtain a valid element id, leaving usage largely to inference from the action enum.

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