Skip to main content
Glama

Respond to browser task

task_respond
Destructive

Perform one action from the current observation in the user's browser (click, type, select, press a key, navigate, scroll and similar), resolve an uncertain effect, mark the task done, or report it blocked. Actions can change or submit data on websites; risky ones pause for the user's approval in Chrome, and an action whose effect is uncertain is never repeated automatically. BrowserPair dismisses page confirmation dialogs (outcome.dialogs); to answer one OK, repeat that action with acceptDialog: true and the user approves it in Chrome. Downloads need the download capability and the user's approval of each one: a blocked download is listed in outcome.downloads; repeat that action with allowDownload: true to ask the user. BrowserPair never returns file contents. To put a file into a page's file field (an element of kind file, or the button that opens the chooser), use kind upload with file; it needs the file_upload capability and the user's approval. When the task has several tabs, the observation lists them in task_tabs; use kind switch_tab with tabId to go back to one, or kind close_tab with tabId to close one this task opened (opened_by_task) that is not current. The observation's open_tabs lists tabs the user already has open on the task's sites (other_open_tabs counts the rest without naming them); use kind adopt_tab with one of those tabIds to work in it instead of opening a new tab. An adopted tab stays the user's: ending the task never closes it. For responsive QA, kind set_viewport with width/height needs viewport_control and changes only the task-owned tab viewport; BrowserPair resets it when control ends. To have the user do one step on the page (sign in, a CAPTCHA or code, a payment step) and then continue yourself, use kind user_step with a reason. For sign_in or verification you may name a structured method such as passkey, QR code, security key or device approval; BrowserPair asks the user in Chrome, never handles that secret/device factor itself, and returns a fresh observation when they press Continue. When the user should continue themselves (for example to review, sign in or pay), end with kind handoff and a summary: the current tab stays open in front of them and BrowserPair stops acting. Never invent refs that are not in task_state.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes
task_idYes
interaction_generationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

It adds substantial behavior beyond the annotations: risky actions pause for Chrome approval, uncertain effects are never repeated automatically, dialogs and downloads have defined handling, file contents are never returned, adopted tabs stay with the user, viewport changes reset, and user_step secrets are handled by BrowserPair. These details materially help the agent predict side effects and approval gates.

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 purpose is front-loaded, and the detail is justified by a complex 26-kind action model. However, the description is a single dense paragraph with many semicolon-separated clauses, making it harder to scan than a structured list would be.

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 complex browser-control tool with no output schema and annotations that only cover safety, the description covers the major behavioral edge cases: approvals, dialogs, downloads, uploads, tabs, viewport control, user steps, and handoff. It still leaves some action kinds and expectedOutcome semantics less explained, so it is strong but not fully complete.

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?

The description explains key nested parameters and action-specific semantics: acceptDialog, allowDownload, file with kind upload, tabId with switch_tab/close_tab/adopt_tab, width/height with set_viewport, reason/method with user_step, and summary with handoff. It does not cover every parameter, such as expectedOutcome, modifiers, targetRef, or coordinate fields, and the schema itself provides some nested field descriptions.

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 states a specific verb and resource: performing one browser action from the current observation, plus resolving, completing, or blocking the task. It clearly explains the tool's scope through many action kinds, but it does not explicitly differentiate itself from sibling tools such as browser_run or task_observe.

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?

The description gives extensive conditional guidance for sub-actions: use kind switch_tab for tabs, kind user_step for sign-in/CAPTCHA/payment, kind handoff when the user should continue, and acceptDialog/allowDownload for dialogs and downloads. It lacks explicit when-not-to-use guidance or named alternatives among the sibling tools.

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