Skip to main content
Glama

Add picture

add_picture

Add a picture or a drawing (handwriting) to the end of a note, the same as inserting one in the app. Pass the image as base64 in data (PNG, JPEG, GIF or WebP, up to 10 MB) or an https address in url. kind "drawing" is for handwriting or a sketch on a transparent PNG: it shows like one drawn in the app's pen, adapts to the theme and can be edited with the pen; a photo or scan of handwriting on paper is a "picture". Without a note, a picture is stored and its Markdown comes back, to place with capture or update_note's append_text. To make a new note with a picture, capture it first, then add the picture. Every image is re-encoded on the way in, so only its pixels are kept. An account can store a few hundred pictures a day.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "add_picture"
  }
}

Input Schema

NameRequiredDescriptionDefault
inkNoDrawings only: dark (default) for strokes drawn to be seen on a light page, light for strokes meant for a dark one.
urlNoOr an https address to fetch the image from.
dataNoThe image, base64 encoded (a data: URL is fine).
kindNopicture (default) or drawing.
noteNoThe note to add it to. Its id (from any other tool's output) or its exact title.
captionNoOptional caption shown under it, up to 300 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Goes well past the annotations (which only say non-read-only, non-destructive, non-idempotent, closed-world): it discloses a 10 MB cap, accepted formats, that every image is re-encoded so only pixels are kept, that drawings adapt to the theme and stay pen-editable, that a note-less call returns Markdown instead of attaching, and a daily quota of a few hundred pictures per account. Those are exactly the operational facts an agent needs before writing.

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 action and the picture/drawing distinction, and nearly every sentence carries a distinct fact (formats, size, re-encoding, no-note return, ordering, quota). It is a single dense paragraph, though, so the quota and re-encoding notes are easy to miss and would read better as separate lines.

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 six-parameter, zero-required mutation with no output schema, the description covers input formats, size limits, the no-note return value, ordering with capture, and rate limits. The only real gap is precedence when both data and url are provided, and the ink parameter is left entirely to the schema.

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 real meaning beyond the schema's terse enum label for kind — explaining that "drawing" is a transparent-PNG sketch rendered like pen strokes and editable, whereas a photo of handwriting is a "picture." It also restates the base64/HTTPS/10 MB input options for data and url, though it does not clarify what happens if both are supplied.

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?

Opens with a specific verb and resource: "Add a picture or a drawing (handwriting) to the end of a note," and immediately distinguishes the two variants (picture vs. drawing) with a concrete criterion (transparent-PNG pen sketch vs. photo/scan). An agent can tell this apart from siblings like capture or update_note 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 Guidelines5/5

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

Gives explicit routing rules and names alternatives: with no note the picture is stored and Markdown is returned "to place with capture or update_note's append_text," and "To make a new note with a picture, capture it first, then add the picture." It also states the when-to-use condition for kind="drawing" versus a "picture," covering both the ordering constraint and the sibling alternative.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources