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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value by enumerating the return content — including which supplier options are infeasible and why — which matters because no output schema exists. It says nothing about cost/latency of the calculation, error behaviour for unknown SKUs, or currency/units of the figures.

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 core statement 'The full calculation for ONE item', then a compact comma-list of outputs, ending with two realistic user-question exemplars that aid intent matching. The enumeration is long but every element maps to a concrete output field, so it earns its place.

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?

For a read-only, single-parameter explain tool with no output schema, the description does the essential work of describing what comes back, including non-obvious elements like infeasibility reasons and payment dates. Only minor gaps remain: units, error behaviour, and how expensive the call is.

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?

There is a single parameter with 100% schema description coverage ('SKU or ERP item id'), so the schema carries the burden and the baseline is 3. The description adds no resolution rules such as whether partial SKUs match, whether an ERP id is preferred over a SKU, or what happens on an unknown item.

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 (explain) and a tightly scoped resource (ONE item), then enumerates exactly what the breakdown contains: demand rate, season factor, safety stock, stock-out date, tranches, and all supplier options. The capitalised 'ONE' contrasts implicitly with aggregate/comparison siblings such as proc_compare_suppliers and proc_plan_get.

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?

The 'ONE item' scoping plus the sample questions ('чому система радить 240 шт', 'що буде якщо взяти дешевшого постачальника') make clear this is the per-item drilldown/why-question tool rather than a comparison or planning tool. It stops short of explicitly naming a sibling to use for multi-item or aggregate questions, so no explicit exclusion is given.

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