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

Annotations already declare a safe, idempotent, closed-world read (readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false). The description adds genuinely new behavioral context beyond that: the per-call scope constraint ('One size per call; for several sizes, call once per size') and the fact that a web-rendered plan link is returned. It does not discuss rate limits or error behavior, but for a read-only calculator that is a minor gap.

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

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

Front-loaded with the purpose, then usage triggers, then the return payload, then the one-size-per-call constraint — a logical order with no filler sentences. It is somewhat dense and long, but every clause carries information (vessel list, output fields, scope rule), so it earns its length without padding.

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

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

With an output schema present, the description needn't enumerate return values, yet it still summarizes them (units per layer, layers, loads needed, utilisation, web link), which is more than required. Annotations cover the safety profile, schema coverage is 100%, and the description supplies purpose, triggers, scope rules and vessel coverage — nothing an agent needs to call this correctly is missing.

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

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

Schema description coverage is 100%, so the schema already documents all nine parameters and the baseline is 3. The description still adds meaning by clarifying that each call covers a single size with optionally-supplied weight, which explains why quantity is interpreted per-size and why weight is optional ('without it the payload is not checked' is in the schema). Modest added value on top of a fully documented schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Plan how one cargo size loads into a shipping container, truck trailer or rail wagon') and enumerates supported vessel types, so the agent knows exactly what the tool computes. It does not explicitly differentiate itself from the overlapping sibling how_many_pallets_fit (which also handles pallets) or calculate_cbm, so it falls short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete trigger conditions: 'Use this when someone asks how many of their boxes, cartons, crates or pallets ... fit in a 20ft, 40ft ... or whether weight or space limits the load.' This clearly states when to reach for the tool. No alternatives are named in the description (get_container_dimensions is only referenced inside the schema), so the 'when-not / alternative' half is missing.

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