Skip to main content
Glama
Sign In

PixelGlass

by co.pixelglass
OverviewDiscussionsAdmin

Preview a theme

preview_theme
Read-onlyDestructive

On one site of the account, named in site. A link that shows the person a theme on their own site as it stands, held changes included: opening it makes that browser, and only that browser, wear the theme on every page for a day; nobody else and no crawler sees it. For a theme that is not the site's, or a change held for its build; the site's own theme with nothing held is simply the site. A client with a browser pane, like Claude Desktop, can open it beside the chat. Optionally a path to land on, and sample: true to show fifty sample posts in place of the site's — a fuller publication to judge a theme on; nothing is saved, and the bar has the toggle.

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": "preview_theme"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoWhere the link lands; / by default
siteYesThe site to work on, as list_sites names it
themeYes
sampleNoShow fifty sample posts instead of the site's own; false by default

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, but the description adds genuinely useful behavior: the effect is scoped to one browser for one day, invisible to others and to crawlers, and nothing is persisted. It also discloses that sample mode shows fifty placeholder posts and that the preview bar carries the toggle. It stops short of saying what happens when the theme or path is invalid.

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?

Information density is high with little filler, but the structure is weak: it opens with a prepositional fragment rather than the action, and the sentence "For a theme that is not the site's, or a change held for its build; the site's own theme with nothing held is simply the site" is grammatically broken and hard to parse on first read.

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?

With no output schema, the description correctly carries the return value (a link) and explains the link's lifetime and scope. For a four-parameter, non-mutating preview tool with annotations present, the remaining gaps (error cases, whether the link can be revoked early) are minor.

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 undocumented parameter is `theme`, which the description does explain: it can be a theme that is not the site's or a change held for its build, and the site's own theme with nothing held yields the plain site. `path` and `sample` are largely restated from the schema, but the added `theme` semantics compensate for the coverage gap.

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 states a concrete verb and resource: it produces "a link" that shows a person a theme on their own site, with held changes included. That distinguishes it in spirit from activate_theme (nothing is saved) and build_theme, but it never names those siblings explicitly, and the opening fragment "On one site of the account, named in site" delays the actual action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the reader can infer this is for judging a theme before activating it, and the note about the site's own theme with nothing held being simply the site hints at scope. There is no explicit when-not guidance, no mention of activate_theme or build_theme as alternatives, and no prerequisites such as needing the theme to exist first.

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