Skip to main content
Glama

Fill browser fields or perform a supported app task

app_action
Destructive

Use this when the user needs to fill 1–20 form fields in one selected Chromium tab or perform one supported application task on a paired computer. Browser form writes verify the exact origin, specified prior field values and resulting values. App tasks use the existing scoped permissions. Changes require commit=true and a unique operation_id UUID; otherwise the tool previews the action. Read-only inspections do not require commit. It does not automatically submit forms or run arbitrary scripts or commands.

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": {
      "mode": "<mode>",
      "device": "<device>"
    },
    "name": "app_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYesExecution backend: one browser form batch or one existing registered application intent.
taskNoapp_task: one registered app intent; not arbitrary code, selectors, commands or coordinates.
commitNoExplicitly authorize one local mutation. Read-only app inspection does not require commit.
deviceYesReMCP device id returned by list_devices. Required for every device operation.
fieldsNobrowser_form: exact label or CSS selector, new value, optional old value / HTML-kind CAS guards.
originNobrowser_form: exact http(s) origin without path, credentials or query. Checked inside the same page evaluation.
dry_runNoReturn the bounded plan without touching the target.
endpointNoOptional local CDP endpoint, loopback-only.
target_idNobrowser_form: exact target id from browser_tabs.
timeout_msNoOperation timeout hint in milliseconds, 100–12000.
operation_idNoUnique caller UUID for every committed mutation; same-id retry is blocked across worker restarts by a private on-disk journal; the caller must inspect uncertain results.

Output Schema

NameRequiredDescriptionDefault
dataNoArray/scalar payload wrapper used when the natural result is not an object.
textYesConcise human-readable result of the tool call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (destructive, non-idempotent, open-world), the description discloses real operational behavior: mutations require commit=true plus a unique operation_id UUID or the call merely previews, origin and prior/resulting values are verified, scoped app permissions are reused, and neither forms nor scripts are executed automatically. That is materially more than destructiveHint/idempotentHint convey.

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?

Sentences are front-loaded with the trigger condition, then constraints, then exclusions, and each carries distinct information. Some sentences are dense and compound (commit + operation_id + preview in one line), but nothing is redundant 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 dual-mode, 11-parameter tool with a nested task object and an output schema, the description covers both backends, safety gating, CAS verification, and the no-auto-submit limit. Remaining gaps are minor: it does not characterize the supported app intent set or error/uncertainty handling, though the latter is partly addressed in the schema.

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 coverage is 100%, so the baseline is 3; the description adds meaning on top by framing field batches as 1–20, explaining that origin is checked inside the same page evaluation, and tying commit/operation_id to the preview-vs-mutate distinction. It does not elaborate on the mode enum's practical implications or timeout behavior, keeping it short of a 5.

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 uses specific verbs and resources: fill 1–20 form fields in one selected Chromium tab, or perform one supported application task on a paired computer. It also states exclusions (no auto-submit, no arbitrary scripts), so an agent can distinguish the two modes. It stops short of naming overlapping siblings such as browser_fill_form or app_task, which would have made it a 5.

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 a clear triggering condition ("Use this when the user needs to fill 1–20 form fields... or perform one supported application task") and clarifies the commit/dry-run split and that read-only inspections skip commit. What is missing is explicit routing against the many sibling tools that overlap in name, so the agent must infer the boundary itself.

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.

Resources