Skip to main content
Glama

Moltline Vision Maths

by com.moltlinestudio

Bbox Convert

bbox_convert
Read-onlyIdempotent

Convert bounding boxes between COCO, Pascal VOC and YOLO. FREE.

The three formats disagree on everything: COCO is [x, y, width, height], VOC is [x1, y1, x2, y2], YOLO is [cx, cy, w, h] normalised to the image. Getting this wrong produces boxes that look plausible and quietly ruin every metric. Typical input {"boxes": [[10, 20, 100, 50]], "from_format": "coco", "to_format": "yolo", "image_width": 640, "image_height": 480} returns {"boxes": [[0.0938, 0.0938, 0.1562, 0.1042]], "converted": 1, "rejected": []}.

Use whenever a dataset and a model disagree about format. Not for scoring predictions (detection_metrics) and not for removing overlaps (nms). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "boxes must contain at least one box"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
clipNoWhen true, clamp boxes to the image bounds instead of returning them as they are. Off by default, because a box outside the image is usually a bug worth seeing.
boxesYesBoxes to convert, each a list of exactly four numbers in from_format, e.g. [[10, 20, 100, 50]].
to_formatYesThe format to convert to; same three choices.
from_formatYes"coco" for [x, y, w, h], "voc" for [x1, y1, x2, y2], or "yolo" for normalised [cx, cy, w, h].
image_widthNoPixel width, required whenever yolo is on either side.
image_heightNoPixel height, required whenever yolo is on either side.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint, and the description confirms and augments these with concrete behavioral details: it 'never raises a protocol error' but returns an error object instead, and provides a full typical input/output example. This adds meaningful context beyond the structured annotations.

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?

The description is compact and front-loaded: purpose first, then formats, example I/O, usage boundaries, error behavior, and idempotence. Every sentence carries distinct useful information with no filler or redundant restatement.

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

Completeness5/5

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

For a conversion tool with full input schema, annotations, and an output schema, the description covers all necessary context: format definitions, coordinate pitfalls, an example transformation, error handling, retry safety, cost, and sibling tool exclusions. It is complete enough for an agent to select and invoke the tool correctly.

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 semantic value by explaining the coordinate conventions ('COCO is [x, y, width, height], VOC is [x1, y1, x2, y2], YOLO is [cx, cy, w, h] normalised to the image') and by clarifying when image dimensions are required. The clip parameter's rationale ('a box outside the image is usually a bug worth seeing') also goes beyond the schema.

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 opens with a specific verb and resource: 'Convert bounding boxes between COCO, Pascal VOC and YOLO.' It clearly distinguishes itself from siblings with explicit exclusions: 'Not for scoring predictions (detection_metrics) and not for removing overlaps (nms).'

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?

The description explicitly states when to use the tool: 'Use whenever a dataset and a model disagree about format.' It also names alternatives and exclusions, and explains that after correcting errored input it is always safe to retry, giving clear operational guidance.

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

All Moltline Vision Maths toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0
Disambiguation5/5

Each of the six tools addresses a clearly distinct operation: bbox_convert handles format transforms, nms removes duplicate detections, detection_metrics evaluates predictions, image_probe reads headers, resize_plan computes resize parameters, and colour_check checks WCAG contrast. There is no overlap or ambiguity between them.

Naming Consistency3/5

Most tools follow a noun_verb pattern (bbox_convert, colour_check, image_probe, resize_plan) but two are outliers: detection_metrics is noun_noun and nms is an acronym. Naming is readable but not fully consistent across the set.

Tool Count5/5

Six tools is a well-scoped count for a vision/maths utilities server. Each tool covers a distinct, necessary facet of computer vision workflows (conversion, suppression, metrics, probing, planning, contrast), with no apparent bloat or trivial tools.

Completeness4/5

The tool surface covers the core calculation needs for bounding-box-based vision tasks: conversion, NMS, evaluation, image metadata, resize planning, and accessibility contrast. Missing features like actual image manipulation or geometric transforms are outside the stated 'maths' scope, so coverage is strong. One could argue for a tool that applies resize to boxes, but resize_plan already returns the transform parameters, which is sufficient.

Resources