Skip to main content
Glama

Run a browser step by name

browser_action
Destructive

Runs one step in an open browser by a Playwright MCP tool name and its arguments. The browser_ tools are the same steps with their own arguments; use this one only for a step they do not list. Takes the session_id from open_browser. 0.1¢ a step that runs.

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": {
      "tool": "<tool>",
      "session_id": "<session_id>"
    },
    "name": "browser_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolYesA Playwright MCP tool name (browser_navigate, browser_snapshot, browser_click, browser_type, browser_take_screenshot and the others), or browser_read for the page's text.
argumentsNoThe tool's arguments, as Playwright MCP names them. browser_read takes format: markdown (default) or text.
session_idYesThe browser session's id, as the opened browser returned it.

Output Schema

NameRequiredDescriptionDefault
urlNo
errorNo
titleNo
resultNo
read_atNo
took_msNo
price_usdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "error": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "price_usd": {
      +      "type": "number"
      +    },
      +    "read_at": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "result": {
      +      "items": {},
      +      "type": "array"
      +    },
      +    "title": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "took_ms": {
      +      "type": "integer"
      +    },
      +    "url": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / session_id / description
      Added value: +"The browser session's id, as the opened browser returned it."
  3. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the risk profile is covered structurally. The description adds genuinely new context beyond that: the per-step cost ("0.1¢ a step that runs") and the fact that the tool proxies arbitrary Playwright steps, which explains why side effects and network access are unbounded. It does not mention error behavior when an unknown tool name is passed.

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?

Four short sentences with zero filler: purpose first, then routing rule, then session provenance, then cost. The routing constraint — the most decision-relevant sentence — is near the front, and nothing is repeated.

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?

With rich annotations, a 100%-covered schema, and an output schema in place, the description supplies the pieces the structured data cannot: fallback routing, cost, and step semantics. The only real gap is what happens on an invalid or disallowed tool name, which matters for a destructive open-world dispatcher.

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 100%, so both the tool pattern and the free-form arguments object are already documented, including the browser_read format option. The description's only addition is that session_id comes from open_browser, which largely restates the schema's "as the opened browser returned it." Baseline 3 is appropriate when the schema does the heavy lifting.

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 — "Runs one step in an open browser by a Playwright MCP tool name and its arguments" — and immediately distinguishes itself from the whole browser_* family. An agent can tell this is a generic dispatcher/fallback rather than a concrete browser action.

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?

Gives an explicit routing rule: the browser_ tools are the same steps, so "use this one only for a step they do not list." That is both a when-to-use and a when-not-to-use condition, which is exactly the guidance a fallback dispatcher needs.

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.