Skip to main content
Glama

apply_css

Preview CSS changes on a shared browser tab without saving; each call replaces the prior preview and navigation clears it before you check the result and save the style.

Instructions

Preview CSS on a shared tab without saving it. Each call replaces the previous preview on that tab; navigation clears it. Check the result with screenshot, then save_style.

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": {
      "css": "<css>"
    },
    "name": "apply_css"
  }
}

Input Schema

NameRequiredDescriptionDefault
cssYes
tabNoTab handle from list_tabs, e.g. "chrome:812". Optional when only one tab is shared.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
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 well: it discloses that the change is non-persistent, that successive calls overwrite the prior preview on the same tab, and that navigation discards it. It does not mention permission/prerequisite requirements for a 'shared tab' or what the call returns, which keeps it from a 5.

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?

Three short sentences, each carrying distinct information: purpose, lifecycle/overwrite behavior, and next steps. The transient nature is front-loaded where an agent will see it first.

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?

For a two-parameter, non-annotated preview tool with no output schema, the description covers purpose, statefulness, invalidation, and the verification/persistence path. The remaining gap is the semantics of the css payload and any return information, which leaves it slightly short of complete.

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 only 50%, and the undocumented parameter is the required one (css) – the description only implies it is raw CSS text via the verb 'Preview CSS', without stating format or whether it is a full stylesheet. The tab parameter's meaning is already fully covered by the schema, so the description adds little there.

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 uses a specific verb+resource ('Preview CSS on a shared tab') and immediately qualifies scope with 'without saving it', which separates it from save_style. An agent can tell what this does and what it does not do without opening any schema.

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?

It gives an explicit follow-up workflow: verify with screenshot, then persist with save_style, naming two siblings. It also implicitly rules out manual cleanup by explaining that each call replaces the previous preview and navigation clears it. It stops short of an explicit when-not statement (e.g., when to prefer editing a saved style directly).

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