Skip to main content
Glama
Sign In
Tester Agent

Tester Agent

by datb2404981
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Mắt của AI: nhìn giao diện thật bằng hình ảnh

tester_browser_see

Captures the current browser view as a JPEG with accessibility tree, viewport size, and JavaScript errors so multimodal models can inspect UI state and detect issues after page loads or actions.

Instructions

Trả về JPEG trực tiếp dưới dạng ảnh MCP cùng accessibility tree, kích thước viewport và lỗi JS. Dùng sau khi mở trang hoặc mỗi thao tác để model đa phương thức tự quan sát và phát hiện lỗi giao diện.

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": {
      "project": "<project>"
    },
    "name": "tester_browser_see"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose the return payload (image, a11y tree, viewport, JS errors), which is the most important behavior for this tool, but it never says whether the call merely captures or also performs navigation/waits, whether it has side effects, or what the latency/cost of a screenshot is.

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?

Two short sentences: the first front-loads what is returned, the second gives the timing. No filler or repetition, though the return payload is enumerated in a slightly dense run-on clause.

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

Completeness3/5

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

No output schema exists, and the description does a reasonable job listing the four things returned, so return-value ambiguity is mostly covered. However, for a tool that implies a live browser session there is no explanation of the 'project' parameter, session state, or failure modes, leaving meaningful gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one required parameter, 'project', with 0% schema description coverage, and the description never mentions it. The agent must guess whether it is a project name, ID, or path and whether it selects the browser session being captured. With low coverage the description should have compensated and does not.

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?

States a concrete verb+payload: returns a JPEG as an MCP image together with the accessibility tree, viewport size and JS errors. That is specific enough for an agent to know it is the 'look at the page' tool rather than an audit or assertion tool. It stops short of naming a sibling it is not (e.g. tester_browser_inspect or tester_browser_layout_audit), so differentiation is implied 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?

'Dùng sau khi mở trang hoặc mỗi thao tác' gives a clear triggering context: call it after navigation and after each action. It does not say when NOT to use it or point to the overlapping observation/audit siblings, which keeps it below 5.

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

Deploy Server

Other Tools