Skip to main content
Glama
SoapyRED

FreightUtils MCP Server

uld_lookup

Read-onlyIdempotent

Get air-cargo ULD specifications—dimensions, weights, volume, deck position, and compatible aircraft—by IATA code or slug, with category and deck filters.

Instructions

Look up air-cargo ULD (Unit Load Device) specifications — 16 types spanning lower-deck containers (AKE/LD3 and family), main-deck pallets (PMC, PAG and family) and temperature-controlled units. Each record carries external/internal/door dimensions (cm), tare and max gross weight (kg), usable volume (m³), deck position and compatible aircraft.

Provide type as an IATA code ("AKE", "PMC") or slug ("ake-ld3"); omit it to list all 16; category (container | pallet | special) and deck (lower | main) filter the list.

Behavior: read-only; an unknown type errors with the valid list; per-record provenance (sources, audited_at, decision_rationale) is included. Rate-limited (anonymous use: 25 requests/day per IP): a 429 error body carries retry_after_seconds and a Retry-After header — back off and retry, or call get_subscribe_link for higher limits.

Returns: the ULD record (or filtered list) under result, plus confidence, _source and citation (the FreightUtils v1 response envelope).

Limitations: specs are compiled from manufacturer and carrier-published sources with ≥7 cited sources per record. Provenance is PENDING, not verified — read the envelope's provenance_status rather than this sentence. Second-agent coverage is now COMPLETE — every cited record-URL pairing has been opened and verdicted by a second agent, and 145 of 148 citations carry a timestamped read (the 3 without one were never opened, and say so). COVERAGE IS NOT AGREEMENT, which is why provenance is still pending: reading every page is what made the disagreements visible, not what resolved them. The second agent also WITHDRAWS stamps — pages a first pass had confirmed turned out not to list the code, or to disagree once somebody read the words around them — so treat an unstamped citation as evidence that was tried and failed, not evidence not yet gathered. CORROBORATION IS COUNTED BY PUBLISHER, NOT BY URL: the 148 citations resolve to 125 distinct sources, because several records cite one publisher at several of its own addresses (one carrier's pallet table appears in three of its documents) and several forwarders republish a single upstream template. Two citations of the same source cannot corroborate each other, so a long source list is not the same as a well-corroborated record. Treat tare_weight with particular caution: it is confirmed by no non-tertiary source on 13 of the 16 records. PGA's 565 kg is now read-confirmed by one carrier (Cathay, basis stated on the page as including nets) while two other carrier pages publish 535 kg and 505-545 kg on that same basis, so it is the top of a contested band rather than an agreed figure. Confidence is medium and a PROVENANCE_PENDING advisory rides every response. Pallet records (PMC, PAG, PGA, PLA, PAJ, PMCQ7) have NO internal dimensions — a pallet has no walls or roof; read max_build_up_height_cm for the aircraft contour ceiling and do not multiply dimensions to get a volume. Airline-specific ULD variants still differ; confirm operationally critical dimensions with the carrier.

Related: chargeable_weight_calculator (what the cargo inside is billed at), container_lookup (the sea-freight equivalent), airline_lookup (whose aircraft it flies on).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
deckNoFilter by deck position.
typeNoIATA ULD code or slug. Examples: "AKE", "PMC", "ake-ld3". Omit to list all 16.
categoryNoFilter by ULD category.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYes
resultYes
_sourceYes
citationYes
validityNo
warningsNo
confidenceYes
blocking_errorsNo
envelope_versionYes
normalized_inputNo
Install Server

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/destructive annotations, it discloses unknown-type error behavior, rate limiting with 429 and retry_after_seconds, Retry-After header, pending provenance status, and pallet-specific caveats like no internal dimensions. This is rich, honest behavioral context. It is also consistent with the annotations.

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?

The description is long but front-loaded with the core look-up purpose and organized into explicit sections: behavior, returns, limitations, and related tools. The length is mostly justified by substantive caveats; however, the limitations paragraphs are unusually verbose and repetitive in places,

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?

It covers input values, return envelope structure, error and retry behavior, rate limits, data provenance, domain-specific caveats about pallet dimensions and weight figure reliability, and related tools. Combined with the 100% schema coverage and an output schema, an agent can invoke and interrogate this tool safely.

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?

The input schema already documents all parameters at 100% coverage, including the same examples ('AKE', 'PMC', 'ake-ld3') and filters. The description adds little beyond restating filter behavior and the omission rule, so the high baseline of 3 is appropriate.

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 precise verb and resource — 'Look up air-cargo ULD specifications' — and immediately scopes 16 types across lower-deck containers, main-deck pallets, and temperature-controlled units. It differentiates itself from siblings like container_lookup and airline_lookup via the Related line, so an agent can tell them apart.

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?

Usage is explicit: provide IATA code/slug or omit for a full list, and use category/deck to filter. The Related line gives alternative tools with clear one-phrase distinctions: chargeable_weight_calculator for billing, container_lookup for sea freight, airline_lookup for aircraft. It lacks an explicit 'do not use when...' but the alternatives are stated.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SoapyRED/freightutils-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server