Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Add a font

add_font
Destructive

Adds a font by its role: display (headlines), body, mono or accent. Either a Google Fonts family by name (google: true; Marsell fetches it), or the font's own file (WOFF2, TTF or OTF; a TTF or OTF is turned into WOFF2) from a public https url or its bytes. Headline and body set the brand kit; mono and accent are kept with the brand's files. For the families Marsell ships, fill_setup's display_font and body_font are enough. For files on the agent's own machine, get_upload_link gives an address to send them to from your shell, so nothing big passes through your messages.

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": {
      "family": "<family>",
      "role": "<role>"
    },
    "name": "add_font"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoA public https address of the file. Marsell fetches it itself (public addresses only, up to 8 MB).
roleYesdisplay (headlines) or body set the brand kit; mono and accent are kept with the brand's files.
familyYesThe family's name.
googleNotrue: fetch the family from Google Fonts instead of sending a file.
filenameNoIts file name with its extension, when you have one.
data_base64NoOr the file's bytes, base64 (as large as one MCP message carries, about 4 MB).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already flag destructiveHint and openWorldHint, and the description adds real context beyond them: display/body overwrite the brand kit while mono/accent are merely stored alongside brand files, TTF/OTF inputs are converted to WOFF2, and Marsell performs the fetch server-side. It stops short of saying whether an existing display/body font is replaced or rejected, which is the one thing an agent about to overwrite a brand kit would want to know.

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?

Front-loaded with the core action and role list, then the input modes, then escalation to sibling tools — a sensible ordering. A few parenthetical glosses (role meanings) repeat the schema, which is the only slight waste in an otherwise dense and purposeful paragraph.

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?

A destructive mutation with no output schema is well served here: the description covers input routing, server-side fetch and conversion, and where each role's result lands. What's missing is the post-call outcome (what the agent gets back, and whether the brand kit is silently replaced), which matters for a destructive write.

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 the exclusivity relationship the schema cannot express — 'either a Google Fonts family ... or the font's own file ... from a public https url or its bytes'. That tells the agent these are alternative paths rather than fields to combine. The role wording is essentially duplicated from 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?

States a specific verb and resource ('Adds a font'), enumerates the four roles with their meaning, and qualifies the two ingestion modes (Google Fonts family vs. a font file). It also distinguishes itself from fill_setup, which handles the families Marsell ships, so an agent can pick the right tool without opening a schema.

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

Usage Guidelines5/5

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

Gives explicit routing conditions: use google: true for a Google Fonts family, a public https url or raw bytes for a file, fill_setup's display_font/body_font when the family ships with Marsell, and get_upload_link when the file lives on the agent's own machine. When-to-use and when-to-use-something-else are both covered.

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

All Marsell 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