Skip to main content
Glama
Image Annotate MCP

Image Annotate MCP

by Thejiuyi

annotate_image

Starts an image annotation session and returns a localhost URL where users draw boxes, points, or polygons, name them, and save; then collect exact pixel coordinates and cropped templates.

Instructions

Open an annotation session for one or more images and return a localhost URL. The user opens that URL and draws boxes (templates), points (click targets) or free-form polygons joined by straight segments, names them, then hits 保存. Then call annotate_wait to collect the result.

source: local file path | data URL | raw base64 | 'screen' (live screen capture) | a list of any of those for a multi-image session. Omit it to capture the screen. resize_to: optional [width, height]; by default the image is NOT resampled, so coordinates always match the original file.

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": "annotate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
sourceNo
resize_toNo
open_browserNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses that this is a human-in-the-loop session, that it returns a localhost URL the user must open, the drawing modes available, and the save step. It leaves out session lifetime, timeout behavior, and what happens on cancellation.

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 purpose and workflow, then a compact per-parameter block. Every sentence adds information; the workflow sentence is long but earns its length by describing the interactive loop. Minor cost: mixing prose and param notes without clear delimiters.

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?

For a session-opening tool with no output schema and 0% schema coverage on four parameters, the description covers the essential interaction model but leaves two parameters undocumented and says nothing about session lifetime, failure modes, or how the returned URL expires. Adequate but with clear gaps.

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?

Schema coverage is 0% across four parameters, and the description only documents two of them. The `source` and `resize_to` notes are genuinely valuable (accepted formats, screen capture, no resampling by default so coordinates match the original), but `name` and `open_browser` are completely unaddressed in both schema and description.

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?

The description states a specific verb and resource ('Open an annotation session for one or more images') plus the concrete outcome (a localhost URL the user interacts with). It distinguishes itself from siblings by naming annotate_wait as the collection step, so an agent can tell this is the session-opener rather than the result-fetcher.

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?

It gives explicit sequencing: open the session, the user draws and hits 保存, then call annotate_wait to collect results. That is real when-to-use guidance tied to a named alternative. It stops short of when-not-to-use cases (existing session, cancel path, what to do if the user never saves).

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