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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: counting rules (excludes test, spam, duplicates, declined, cancelled, refunded, unpaid), revenue definition (paid orders, COD once accepted, less refunds), currency returned as text, the Free-plan 50-orders-per-UTC-month cap with omittedOverCap, and the visitor-join limitation that makes analytics conversions estimates. That is exactly the behavioral context an agent needs to trust the numbers.

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 use-case trigger and alternatives are front-loaded and no sentence is pure filler, but the body is a dense single block, and the traffic-source definition is effectively stated twice (once for bySource, once for byArrival). Slightly tighter phrasing would make the caveats easier to scan.

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?

There is no output schema, so the description carries the return-shape burden and does: orders and revenue totals, by page, by source dimension, and the byArrival split with the named assistant domains. Plan-tier limitations, date semantics, and the visitor-join caveat are all disclosed, leaving nothing an agent needs in order to call it correctly.

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 is 3; the description adds real meaning on top by explaining that startDate/endDate are whole days interpreted in timeZone, that leaving both out means all time, and by defining what the bySource grouping actually represents (UTM source/medium/campaign or referrer, with "(none)"). siteId's "only this page" semantics are already fully covered by the 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?

The description names a specific verb and resource set — order counts and revenue broken down by page and by traffic source, plus byArrival — and does so in the user's own vocabulary (「どのページが一番売れてる？」「今月の売上」). An agent can separate it from get_orders (raw list) and analyze_source_quality (traffic+orders side by side) without opening either schema.

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 explicitly when to use it ("Use this tool when the user asks how many orders or how much revenue..."), gives concrete example utterances including Japanese ones, and names the alternative plus the condition that selects it ("For traffic and orders by source side by side, use analyze_source_quality"). Little is left to inference.

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