Skip to main content
Glama
Sign In

PixelGlass

by co.pixelglass
OverviewDiscussionsAdmin

Render a page

render_page
Read-onlyDestructive

On one site of the account, named in site. The site's own rendering of one path — "/" for the home page, a post's public path, "/tag/", a site page's own path, a path that does not exist for the theme's 404 (error.liquid) — with the theme as it stands, held changes included, as HTML, without a browser: how you check your own work. Read it for a missing partial, an empty loop, a stray tag, then fix and render again. Long pages are cut at forty thousand characters. When it looks right, hand the person the page's address.

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": {
      "site": "<site>",
      "theme": "<theme>"
    },
    "name": "render_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoA path on the site; / by default
siteYesThe site to work on, as list_sites names it
themeYes
sampleNoRender with fifty sample posts instead of the site's own; false by default

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

The description adds genuinely useful behavior beyond the annotations: HTML output, no browser needed, the theme is rendered as it currently stands with held changes included, and output is truncated at forty thousand characters. However, the annotations declare destructiveHint=true and idempotentHint=false, and the description frames this purely as a read-only self-check without explaining what could be destructive or non-idempotent (cache effects, partial builds, held-change state). That unexplained divergence is a real gap for an agent deciding whether to call it repeatedly.

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 content is dense and mostly earns its place, but the prose is telegraphic and grammatically broken in places — the first sentence is a verbless fragment and em-dash chains make the path list hard to parse. Useful information (path forms, truncation limit, the give-them-the-address step) is present but not cleanly front-loaded behind a clear statement of the operation.

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?

With no output schema, the description correctly carries the return-value burden (HTML, cut at forty thousand characters) and explains the sample flag's effect indirectly. It falls short on two points an agent needs for a four-parameter call: the required theme argument is never explained anywhere, and the declared destructive/non-idempotent behavior is left undisclosed.

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?

Schema coverage is 75% and the description meaningfully extends it, chiefly for path: it enumerates the accepted path forms including the 404 template case, which the schema only summarizes as "/ by default." It also ties site to the account and confirms rendering uses the theme as it stands. The required theme parameter has no description in either the schema or the description, so how to name a theme remains undocumented.

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 makes clear this renders one path of a site's theme to HTML server-side ("without a browser"), and enumerates exactly which path shapes are valid ("/", a post's public path, "/tag/<slug>", a site page path, and a nonexistent path for the 404 template). It is specific about verb and resource, but never names sibling tools like preview_theme, build_theme, or validate_theme, so the agent must infer the boundary itself. The opening fragment ("On one site of the account, named in site") lacks a main verb and weakens the first impression.

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?

Usage is given concretely: "how you check your own work," read it for a missing partial, empty loop, or stray tag, then fix and render again, and finally give the person the page address. That is a real when-to-use and a follow-on workflow. There are no explicit when-not conditions and no named alternatives (preview_theme would be the obvious contrast), which keeps it below a 5.

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

All PixelGlass 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