Skip to main content
Glama

Run a batch of page actions

browser_batch

Run multiple browser actions on the current page in one turn: fill/check/hover/type/focus in parallel, other actions in sequence; return per-action results and a compact diff.

Instructions

Execute several actions on the current page in one turn. Fill/check/hover/type/focus run in PARALLEL with cloned multi-cursors; everything else runs SEQUENTIALLY because it can change the page. Drag takes a destination ref in "value" (e.g. value "e8"); upload takes file path(s); reload/back/forward/dialogAccept/dialogDismiss take no ref. Returns a per-action report, obstacle diagnostics for failed clicks, and a compact "+ / -" diff.

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": {
      "actions": "<actions>"
    },
    "name": "browser_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoNavigate to this URL before running the batch.
actionsYesOrdered list of actions to execute.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4/5.0
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 substantial work: it discloses the parallel vs sequential execution model, why certain actions must be sequential ('because it can change the page'), and the return shape including per-action reports, obstacle diagnostics for failed clicks, and a '+ / -' diff. The main undisclosed behavior is failure handling — whether one failed action aborts the remaining batch or is reported and skipped — which matters a lot for a multi-step tool.

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 dense sentences, front-loaded with the core purpose and then the execution semantics, then the per-action argument quirks, then the return contract. Every clause carries information an agent needs to build a correct call; nothing is filler.

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 tool with 19 possible actions, a polymorphic value field, no annotations, and no output schema, the description covers purpose, ordering semantics, argument quirks, and return contents. What is missing is batch-level error semantics (partial failure, abort behavior) and any size or ordering constraints on the actions array, which an agent would want before composing a long batch.

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 description coverage is 100%, so the baseline is 3. The description does disambiguate the polymorphic 'value' field (destination ref for drag, file path(s) for upload) and lists which actions take no ref, but the schema's own property descriptions already state these same mappings, so the description mostly restates rather than adds. It adds no guidance on ordering interactions or timeout behavior beyond what the schema documents.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'Execute several actions on the current page in one turn.' That is far more informative than the title alone and makes clear this is the multi-action path rather than a single-step tool like navigate or snapshot. It stops short of naming any sibling to route against, so differentiation is inferred from scope rather than stated.

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?

It gives real when-to-use context: batch several actions 'in one turn' instead of issuing them one at a time, and it explains the concurrency model that determines whether actions can safely be combined (fill/check/hover/type/focus parallel, everything else sequential). There are no explicit exclusions telling the agent when to prefer a single-action sibling, which keeps this below a 5.

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