Font Design MCP

Overview Schema Source Related Servers Discussions Admin

reference_import

Import a bounded single-frame PNG from workspace/inbox as an immutable drawing reference for glyph design, mapping image pixels to font units via image_to_font and requiring expected_revision.

Instructions

Import a bounded single-frame PNG from workspace/inbox as an immutable drawing reference. image_to_font maps image pixels (top-left, Y down) to font units (baseline, Y up). Requires expected_revision. No tracing or automatic rescaling; use reference_id with render_glyph.

Input Schema

TableJSON Schema

Name	Required	Default
`crop`	No
`label`	No
`replace`	No
`summary`	No
`glyph_id`	Yes
`image_mode`	No	inline
`project_id`	Yes
`source_path`	Yes
`reference_id`	Yes
`image_to_font`	Yes
`expected_revision`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	Yes
`data`	No
`error`	No
`changed`	No
`summary`	Yes
`revision`	No
`warnings`	No
`project_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.6.0Sep 12, 2026

addedInput schema / properties / crop

Added value: +{
+  "anyOf": [
+    {
+      "maxItems": 4,
+      "minItems": 4,
+      "prefixItems": [
+        {
+          "maximum": 2048,
+          "minimum": 0,
+          "type": "integer"
+        },
+        {
+          "maximum": 2048,
+          "minimum": 0,
+          "type": "integer"
+        },
+        {
+          "maximum": 2048,
+          "minimum": 1,
+          "type": "integer"
+        },
+        {
+          "maximum": 2048,
+          "minimum": 1,
+          "type": "integer"
+        }
+      ],
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

Addedv0.5.0Sep 10, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations only tell the agent it is a non-read-only, non-destructive, non-idempotent operation. The description adds real behavioral context not in structured fields: the image_to_font pixel-to-font-unit convention (top-left, Y down → baseline, Y up), the immutability of the resulting reference, and the concurrency requirement (expected_revision). It omits the effect of `replace` and image_mode, but adds substantial value.

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?

Three tightly packed sentences with the core action front-loaded and constraints following. No filler, though the mapping sentence and the trailing guidance could be split more clearly for scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, and annotations cover the safety profile. Still, for a mutation tool with 11 mostly-undocumented parameters, the description leaves gaps (crop semantics, replace behavior, image_mode) that an agent must guess at.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 11 parameters, so the description must compensate. It usefully explains image_to_font and flags expected_revision, but leaves crop, label, replace, summary, image_mode, source_path, glyph_id and reference_id entirely undocumented, which is most of the surface.

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 (Import), resource (bounded single-frame PNG), source location (workspace/inbox) and its nature (immutable drawing reference). An agent can distinguish this from siblings like glyph_edit or render_glyph 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 Guidelines3/5

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

It points forward ("use reference_id with render_glyph") and excludes behaviors ("No tracing or automatic rescaling"), which is useful. However, it never says when to choose this import over other workflows or what prerequisites/preconditions apply beyond requiring expected_revision.

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