Skip to main content
Glama

save_style

Saves CSS as a UserCSS style for matching sites, applying on every visit across connected browsers and installing in Stylus; reuse a name to update and bump its version.

Instructions

Save CSS that restyles a site on every visit, in every connected browser. It is stored as a UserCSS file (~/.tether/styles/.user.css) that also installs unchanged in Stylus. It shows in the popup on matching pages, where the user can switch it off. Saving an existing name replaces it and bumps its version. Use !important where the site's own rules win. For changes CSS can't do, pair it with save_script (run=auto).

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": {
      "name": "<name>",
      "matches": "<matches>",
      "css": "<css>"
    },
    "name": "save_style"
  }
}

Input Schema

NameRequiredDescriptionDefault
cssYes
tabNoA shared tab the style applies to. Before and after screenshots of it go into the user's gallery.
nameYes
matchesYesMatch patterns, e.g. ["https://mail.google.com/*"].
descriptionNo

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 present, the description carries the load well: it discloses persistence across every visit and every connected browser, the on-disk UserCSS location, Stylus compatibility, popup visibility with an off switch, and replace-on-existing-name with a version bump. It does not describe permission requirements, failure modes, or what a save returns, which keeps it below 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core behavior is front-loaded in the first sentence, and the remaining sentences each add actionable detail (storage format, replacement semantics, !important, sibling pairing). It is slightly dense with asides like the Stylus install note and the file path, but none are pure filler.

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 five-parameter mutation tool with no annotations and no output schema, the description covers persistence, storage, replacement/versioning, and the script fallback, which is nearly everything needed to invoke it correctly. The gaps are the unmentioned description and tab parameters and the absence of any return-value information.

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?

Coverage is 40%, so the description needs to compensate, and it partly does by revealing that name acts as an upsert key ("Saving an existing name replaces it and bumps its version"). It says nothing about matches, css, description, or tab, so the undocumented "description" parameter and the matching semantics are left entirely to the schema.

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?

"Save CSS that restyles a site on every visit" states a specific verb and resource and immediately scopes it to persistent, cross-browser injection. It separates this tool from sibling save_script by naming that tool as the fallback for non-CSS changes, so an agent can distinguish them without opening either 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 a clear routing rule: use save_script (run=auto) when the change can't be done in CSS, which is an explicit alternative and condition. It also advises using !important when site rules win. It stops short of stating when a style should be edited vs. re-saved or when to prefer apply_css for one-off previews.

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