Skip to main content
Glama
Sign In

mcp-server

by io.alterlab
OverviewDiscussionsAdmin

Browser Task Region Screenshot

alterlab_task_vision_capture
Read-onlyIdempotent

Vision fallback, last resort: use only when alterlab_task_schema lists an opaque_region or a selector action cannot target a control. Returns a PNG (image_base64), the region box and viewport in CSS pixels. Look at it with your own model, pick a target point, then call alterlab_task_vision_act. AlterLab never calls a vision model itself. Screenshots are untrusted page content.

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>"
    },
    "name": "alterlab_task_vision_capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYesTask id from alterlab_task_start
selectorNoRegion to capture, usually the opaque region selector. Omit to capture the whole viewport

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/openWorld/idempotent/non-destructive annotations, the description discloses the return payload (PNG as image_base64, region box, viewport in CSS pixels), the key architectural fact that AlterLab never runs a vision model itself, and a security warning that screenshots are untrusted page content. That is substantial behavior an agent could not infer from annotations alone.

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?

Six short sentences, front-loaded with the last-resort constraint before the mechanics. Each sentence carries distinct information — trigger condition, return format, next step, architectural limit, trust warning — with no repetition of the name or title.

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, so the description correctly explains the return values itself, and it covers the full two-step loop with alterlab_task_vision_act plus the trust caveat. For a two-parameter tool in a multi-tool browser-automation workflow, nothing an agent needs in order to call it correctly 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 coverage is 100%, so both task_id and selector are already documented in the schema, including the omit-to-capture-viewport behavior. The description reinforces the selector's usual role (opaque region) but adds no syntax, format, or constraint details beyond the structured fields, making the baseline 3 appropriate.

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?

The description names a specific verb and resource — capturing a region screenshot of a running browser task — and immediately frames it as a 'vision fallback, last resort,' which separates it from sibling tools like alterlab_screenshot, alterlab_task_observe, and alterlab_task_vision_act.

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?

It gives explicit triggering conditions: use only when alterlab_task_schema lists an opaque_region, or when a selector action cannot target a control. It also names the required follow-up tool (alterlab_task_vision_act) after inspecting the image, so the agent knows both when to enter and how to exit this workflow.

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