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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description reinforces this with "No key needed; read-only." Beyond that it adds real behavioral context the annotations cannot: results carry a note on the convention used and are flagged "approximate" or "ambiguous" when a size falls between or spans rows, which tells the agent how to hedge its recommendation. The only shortfall is that it leans on the output schema for the actual result shape.

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?

The trigger condition and the conversion scope are front-loaded, and the long enumeration sentence earns its length by covering genuinely distinct size families. It is dense and would benefit from breaking that one sentence into a short list, but no sentence is filler.

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 three-parameter, read-only lookup with full schema coverage, an output schema, and complete annotations, the description supplies everything an agent needs: which kinds and systems pair, when to invoke it, how to interpret ambiguous results, and how to defer to brand charts. Nothing material 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 coverage is 100%, so the baseline would be 3, but the description adds meaning the schema does not: it maps each `kind` value to the specific systems valid for it (e.g. jeans waist vs. rings in millimetres vs. sneakers with US_M/US_W/CM), which constrains `system` per `kind` in a way the free-text schema field cannot. It also gives concrete size examples matching the schema's format hints.

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?

The description opens with a specific verb and resource ("Convert a size between systems") and then enumerates every supported size family and the systems each accepts, so an agent can immediately tell this apart from sibling tools like get_item or vocabulary. The goal statement ("so the shopper orders the right one") also anchors the purpose in the shopping flow.

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?

It states the exact triggering condition ("whenever the shopper's size and the item's sizes are in different systems") and the sequencing constraint ("before recommending a size"), plus a precedence rule that the brand's own chart always wins. There is no sibling tool performing conversion, so no alternative needs naming, and the guidance leaves nothing to inference.

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