Skip to main content
Glama

Inkscape File

inkscape_file
Destructive

Load, validate, convert, export, and batch-process SVG or other files through Inkscape CLI; inspect metadata and list supported formats for editing and publishing workflows.

Instructions

INKSCAPE_FILE — Load, convert, export, and validate SVG/other files via Inkscape CLI.

PORTMANTEAU RATIONALE: One tool keeps file I/O discoverable without dozens of single-purpose tools; operation selects the CLI behavior.

Operations:

  • load: Read/validate path exists for editing workflows.

  • save: Persist changes (requires paths per server policy).

  • convert: Export to pdf/png/etc. (needs output_path, format).

  • info: Metadata and dimensions.

  • validate: Structural check via CLI query.

  • list_formats: Bounded list of supported export formats (no disk read required).

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": {
      "operation": "<operation>"
    },
    "name": "inkscape_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
latexNo
formatNoTarget format for convert/batch_convert (e.g. pdf, png).
marginNo
qualityNoEncoder quality 1-100 for the Pillow-backed formats (jpeg/webp/avif).
pdf_pageNoPage to read when input_path is a PDF.
operationYesMust be one of the Literal values (schema-enumerated).
input_pathNoSource file; may be empty for list_formats/batch_convert.
output_dirNoDestination directory for batch_convert (required).
input_pathsNoSource files for batch_convert (required for that operation).
output_pathNoDestination for save/convert when applicable.
pdf_versionNo
png_ditheringNo
ignore_filtersNo
png_color_modeNo
validate_structureNoRun Inkscape's query check during load.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotency, so the safety profile is known. The description adds some context beyond that — save requires paths 'per server policy', list_formats needs no disk read, validate_structure runs during load — but it never says which operations overwrite/destroy existing files (e.g. convert writing to an existing output_path) or what the permission requirements actually are.

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 a verb list, then a scannable bulleted operation index — efficient and easy to parse. The 'PORTMANTEAU RATIONALE' paragraph is meta-commentary that earns only marginal value, but it is short and does explain the design choice.

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 15-parameter portmanteau tool with an output schema (so return values need no explanation) and annotations covering the safety profile, the description does enough to orient an agent. The main gaps are the unmentioned batch_convert operation and the missing per-operation destructive/overwrite semantics.

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?

With 15 parameters at 60% schema description coverage, the description must carry weight for the undocumented half. It clarifies format and output_path for convert, implies input_paths/output_dir for batch, and explains validate_structure, but six parameters (latex, margin, pdf_version, png_dithering, png_color_mode, ignore_filters) get no mention anywhere, so the gap is only partly compensated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb set (load, convert, export, validate) and resource (SVG/other files via Inkscape CLI), and the per-operation bullets make the tool's scope legible at a glance. It does not differentiate itself from siblings such as inkscape_analysis, inkscape_metadata, or inkscape_vector, which overlaps likely exist with, so it stops short of a 5.

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?

The operation list gives intra-tool routing for load/save/convert/info/validate/list_formats, which is genuine when-to-use guidance. However, the description never covers `batch_convert` even though it is in the enum and has dedicated parameters (input_paths, output_dir), and it gives no guidance about when to prefer a sibling tool over this one.

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