Skip to main content
Glama
Sign In

URLinks

by me.urlinks
OverviewDiscussionsAdmin

submit_custom_css

Destructive

Submit custom CSS for one or more profile concerns. The CSS is sanitized server-side and stored per-concern. Call get_customization_rules first to understand what selectors and properties are available. CSS must target .pc-* classes only. url() is blocked — use gradients and solid colors. @keyframes are supported.

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>",
      "concerns": "<concerns>"
    },
    "name": "submit_custom_css"
  }
}

Input Schema

NameRequiredDescriptionDefault
cssYesThe CSS to apply. Must target .pc-* classes (e.g., .pc-button, .pc-name). Selectors are auto-scoped. Can include @keyframes, @media, pseudo-classes, and pseudo-elements.
concernsYesWhich concerns this CSS applies to. Valid: background, buttons, header, name, bio, avatar, banner, cards, social, dividers, blocks
source_promptNoOptional: the prompt that generated this CSS (for audit trail)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare destructiveHint=true and readOnlyHint=false; the description adds real value by disclosing server-side sanitization, per-concern storage, the url() block, and @keyframes support. The one material omission is whether submitting replaces any CSS already stored for those concerns, which is the key risk for a destructive tool.

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?

Five short sentences, front-loaded with purpose, then prerequisites and constraints in order of decision importance. No filler or restatement of the tool name.

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 and a destructive write, the description covers sanitization, scoping, and allowed CSS features well. It leaves unresolved what happens on invalid CSS (error vs. silent drop) and whether prior per-concern CSS is overwritten, both of which matter before a destructive submit.

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 100%, so the baseline is 3, but the description adds constraint semantics the schema lacks: url() is blocked, so the agent must use gradients and solid colors. That is actionable meaning beyond the schema's 'must target .pc-* classes' wording.

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 (submit custom CSS) plus scope (one or more profile concerns), which cleanly separates it from get_custom_css and reset_custom_css. The agent knows exactly what the tool does without opening the 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?

Gives an explicit prerequisite: call get_customization_rules first, and states the content constraints that gate a usable call (.pc-* selectors only, no url()). It does not say when to prefer a sibling instead — e.g. update_page_style for non-CSS styling or reset_custom_css to clear overrides — so routing guidance is incomplete but the entry conditions are clear.

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

All URLinks 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