Skip to main content
Glama
Render MCP Server

Render MCP Server

by meiti-dev

render_open

Open a page in a real browser to return an element map with roles, states, positions, measured visual issues, and a session ID for follow-up interactions.

Instructions

Open a page in a real browser and return its MAP: every element that matters (role, name, text, value, state, position) plus visual issues measured exactly (horizontal overflow, cut text, covered or off-screen elements, small touch targets, low contrast, broken images, unnamed buttons). Works inside same-origin iframes. Returns a session id for render_act, render_expect and render_scan.

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": {
      "url": "<url>"
    },
    "name": "render_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
widthNoViewport width. Default 1280; use 375 for a phone.
heightNoDefault 800.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does substantial work: it enumerates what the MAP contains, lists the exact visual issues measured, and discloses iframe handling (same-origin only). Remaining gaps are load/wait semantics, timeouts, and whether a browser session is spawned or reused and how it is disposed of (render_close exists but is not referenced here).

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 its output, followed by a parenthetical enumeration and a short integration sentence; no filler. The middle list of visual checks is long but each item is concrete and load-bearing for deciding whether this tool answers the question.

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?

There is no output schema, so the description must describe the return value — it does, naming both the MAP contents and the session id. For a 3-parameter, non-destructive read-style tool the picture is nearly complete; the only material omissions are timing/readiness behavior and lifecycle management of the opened session.

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 67%: width carries a default and an explicit phone use case (375), height carries a default, but url has no schema description. The description adds nothing about the URL beyond 'open a page' — no guidance on relative vs absolute URLs, auth-required pages, or scheme handling. Baseline 3 is appropriate given the schema does most of the work.

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 (open a page in a real browser) and defines the payload returned (a MAP of elements plus measured visual issues). It also positions itself against siblings by naming render_act, render_expect and render_scan as downstream consumers of the session id, so an agent can tell it is the entry point rather than a continuation.

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 sequencing hint ('returns a session id for render_act, render_expect and render_scan') effectively tells the agent this is the first call in the render workflow. What is missing is any exclusion: it never states when NOT to use it, e.g. whether render_scan can be called on an already-open page or when to prefer render_compare.

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