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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavioral detail: default TOTAL + section-level rows, the chained-index option, the Chinese-only label caveat, and the base period convention. These extend the structured annotations without contradicting them.

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 description is compact and front-loaded, covering resource, metric semantics, parameter usage, defaults, and a caveat in four sentences. The Chinese sentence is redundant for an English-speaking agent but does not materially hurt readability or conciseness.

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 tool with no required parameters and no output schema, this description is remarkably complete: it states the source, metric definition, classification/direction options, chained variant, default aggregation, drill-down mechanism, month behavior, and a localization caveat. An agent has everything needed to make a sensible first call.

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% and the description reinforces every parameter: it enumerates `series` values, explains `direction`, `chained`, `month` omission, and `hs2` drill behavior. It adds value by clarifying defaults and how parameters combine, though the schema already documents the individual parameters well.

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 the exact resource (GACC trade-index tables), the metric family (unit-value, quantum, value indices), the base period, and the default return shape. It is clearly distinct from sibling tools like china_trade_by_commodity or china_trade_summary because it centers on indices rather than commodity-level or country-level trade flows.

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 gives concrete operational guidance: choose `series` and `direction`, use `chained` for the chained variant, omit `month` for the latest month, and pass `hs2` to drill into a chapter. It does not explicitly name sibling alternatives or state when not to use this tool, but the usage context is clear enough from the description.

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