Image Label MCP Server

Export annotations

export_annotations

Read-onlyIdempotent

Export an image's annotations as COCO JSON, YOLO labels, or QuPath GeoJSON for model training or object import.

Instructions

Export an image's annotations: COCO JSON or YOLO (polygons and circles, as the web app exports), or QuPath GeoJSON (File > Import objects in QuPath; nuclei found by StarDist come in as detections).

Input Schema

Name	Required	Description	Default
`format`	No	'coco' (COCO JSON), 'yolo' (YOLO labels and classes) or 'qupath' (QuPath GeoJSON, nuclei as detections).	coco
`image_id`	Yes	Id of an image in Image Label: the imageId (a UUID string) returned by list_images or an upload.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.8.1Oct 28, 2026

addedInput schema / properties / format / description

Added value: +"'coco' (COCO JSON), 'yolo' (YOLO labels and classes) or 'qupath' (QuPath GeoJSON, nuclei as detections)."

addedInput schema / properties / image_id / description

Added value: +"Id of an image in Image Label: the imageId (a UUID string) returned by list_images or an upload."

Changed1 schema field changedv0.3.3Oct 24, 2026

changedInput schema / properties / format / enum

Previous value: -[
-  "coco",
-  "yolo"
-]New value: +[
+  "coco",
+  "yolo",
+  "qupath"
+]

First observedv0.1.0Oct 17, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds genuine behavioral detail beyond that: YOLO exports polygons and circles as the web app does, and QuPath nuclei from StarDist arrive as detections. It doesn't discuss error conditions, but the output schema covers returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler. Parentheticals are dense but each earns its place by clarifying a format's export behavior.

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?

With an output schema, full parameter documentation, and rich annotations, the description is nearly complete for a read-only export tool. It could add one line about when to choose this over export_dataset, but nothing required to invoke it correctly is missing.

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. The description adds meaning beyond the schema's enum: 'as the web app exports' clarifies YOLO semantics, and the QuPath parenthetical explains how nuclei appear as detections, which the schema does not state.

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 ('Export an image's annotations') and enumerates the exact output formats, which distinguishes it from export_dataset (a dataset-level export). An agent can identify the operation and scope 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?

Format-specific context is provided ('as the web app exports', QuPath import steps), which implies when each format is appropriate. However, it never explicitly names alternatives (e.g., export_dataset) or states when not to use this tool, leaving routing to inference.

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