Brimload Container Loading

pack_boxes

Read-onlyIdempotent

Calculate how many identical boxes fit in a rectangular space, and where.

    The space is a shipping container, a pallet area, leftover container space,
    or a larger box. Give the box's L/W/H and EITHER a `container` preset OR the
    space's L/W/H (all in millimetres - container presets are mm). Boxes mix
    orientations across regions to pack densely; the plain maximum-load answer
    uses the exact T1 solver.

    Args:
        box_length: Box length.
        box_width: Box width.
        box_height: Box height.
        container: Container preset instead of explicit space dims (fills the
            internal usable L/W/H in mm; overrides space_* when recognised).
            ISO dry: 20GP 20HQ 40GP 40HQ 45GP 45HQ; NA domestic: 53HC 48HC;
            reefers: 20RF 40RF 40RH; EU pallet-wide: 40HQ-PW 45HQ-PW. Many
            aliases (20/40/45, 20ft, 40HC, 40', 40 reefer, ...).
        space_length: Space length (front-back). Use this OR `container`.
        space_width: Space width (left-right).
        space_height: Space height (up).
        count: How many boxes to load. 0 (default) loads the maximum.
        to_front: Anchor a partial load to the front (else the back).
        to_left: Anchor a partial load to the left (else the right).
        to_bottom: Kept for compatibility, no effect: boxes always rest on
            the floor.
        box_weight: Weight of one box (optional; same unit as max_weight).
        max_weight: Max total load weight (optional; 0 = no weight limit).
        include_image: Set true ONLY when the user wants to SEE or visualize
            the loading plan / 3D layout (e.g. "show the loading plan",
            "visualize it", "what does it look like?"). Default false is
            faster and lighter and still returns `image_url`, a shareable
            link to the 3D render. When true, the image is ALSO embedded
            inline (Claude Desktop and Cherry Studio display it; the
            claude.ai web app shows only the link either way).

    Returns the maximum that fits, how many were loaded, the fill rate, the
    region/block decomposition (each block's position, orientation, and
    grid), any weight limit applied, an `image_url` link to the rendered 3D
    loading plan, and - when include_image is true - the inline image too.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`count`	No
`to_left`	No
`to_front`	No
`box_width`	Yes
`container`	No
`to_bottom`	No
`box_height`	Yes
`box_length`	Yes
`box_weight`	No
`max_weight`	No
`space_width`	No
`space_height`	No
`space_length`	No
`include_image`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 19, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the read-only/idempotent annotations, it discloses non-obvious behavior: boxes mix orientations across regions, the plain maximum uses the exact T1 solver, `container` overrides `space_*`, `to_bottom` is a no-op because boxes always rest on the floor, and inline images only embed on certain clients while `image_url` is always returned.

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?

Long, but justified by 14 parameters, and the purpose plus the container/space rule is front-loaded. There is minor redundancy between the `include_image` prose and the Returns paragraph about `image_url`, but every section otherwise earns its place.

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?

With no output schema, the description fully specifies the return payload (max fit, loaded count, fill rate, region/block decomposition, weight limit, `image_url`, optional inline image) and all input modes. An agent has everything needed to call and interpret it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% with 14 parameters, so the description carries the full burden and does: it specifies millimetre units, enumerates container presets and aliases, documents defaults (count=0 loads max), anchor semantics, and weight units.

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 ('Calculate how many identical boxes fit in a rectangular space, and where') and immediately clarifies the domain (container/pallet/box). It is trivially distinguishable from the sole sibling, send_feedback.

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?

Gives clear conditional guidance: supply EITHER a `container` preset OR explicit space dims, and use `include_image` ONLY when the user wants to see the plan. It handles the key decision points. It does not name alternative tools or state when not to call it, but no relevant alternative exists here.

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

All Brimload Container Loading tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?