Skip to main content
Glama
Sign In

mcp-server

by io.alterlab
OverviewDiscussionsAdmin

Browser Task Click By Coordinates

alterlab_task_vision_act
Destructive

Vision fallback: click the point (x, y in CSS pixels from the viewport origin) you picked from alterlab_task_vision_capture, then verify the result. Pass expect.text for text that should appear, or leave it to check that the page changed. The click is treated as a submit and asks for approval, unless your previous vision click was observed to be plain navigation. Each use is audited, flags the recipe for repair and counts toward a per-run cap, and past the cap it asks again. The result reports the class the click turned out to be. On awaiting_user show the pending request, call alterlab_task_answer, then retry unchanged.

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": {
      "task_id": "<task_id>",
      "x": "<x>",
      "y": "<y>"
    },
    "name": "alterlab_task_vision_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYesHorizontal target in CSS pixels from the viewport origin
yYesVertical target in CSS pixels from the viewport origin
expectNoRead-back check: {"text": "text shown after the click"} or {"changed": true}. Default {"changed": true}
recipeNoRecipe the click belongs to, for standing permissions
task_idYesTask id from alterlab_task_start
selectorNoRegion the point must fall inside; same value passed to capture

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover destructive/non-idempotent/open-world, but the description adds substantive behavior: the click is treated as a submit and requests approval unless the prior vision click was plain navigation, each use is audited, flags the recipe for repair, counts toward a per-run cap, and re-asks past the cap. It also discloses what the result reports (the click's resolved class).

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?

Front-loaded with the action and coordinate semantics, then the approval and cap behavior, then the recovery loop. It is dense but nearly every clause carries operationally relevant information; a slight tightening of the approval/cap sentences would help.

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

Completeness5/5

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

There is no output schema, and the description compensates by explaining what the result reports and the awaiting_user state machine. For a destructive, approval-gated, rate-capped click tool with a nested expect object, nothing essential is missing.

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 x/y units, expect, recipe, and selector are already documented. The description adds only modest meaning, clarifying that an empty expect defaults to checking the page changed and that retries should be sent unchanged; that is a useful but small increment over the schema.

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: click the point (x, y) picked from alterlab_task_vision_capture, then verify. It also positions the tool as a 'vision fallback', which separates it from the sibling alterlab_task_act (selector-based action) without the agent needing to open either schema.

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?

Explicitly frames itself as a fallback used after alterlab_task_vision_capture, gives conditional guidance for expect.text versus leaving it blank, and prescribes a concrete recovery path: on awaiting_user, show the pending request, call alterlab_task_answer, then retry unchanged.

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

All mcp-server toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources