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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar for added value is met by the description's substantive behavioral disclosures: the sign convention for the financial account (positive asset value = net DECREASE), which is a genuine data-interpretation trap, and the lag cadence with a verification date that preempts a 'stale site' misdiagnosis. This is exactly the kind of context beyond what annotations provide. No contradiction with annotations exists.

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 dense but each sentence earns its place: content scope first, then cadence/lag with verification, then the critical sign convention. The verification parenthetical is long but serves a real purpose — preventing an agent from incorrectly flagging the data as stale. Slightly more verbose than strictly necessary, but no 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?

There is no output schema, so the description partially carries the burden of conveying what the agent will receive; it succeeds on the riskiest aspects — data contents, frequency, and sign convention. What it does not specify is the return structure (e.g., row shape, how quarters are labeled, whether values are scaled). For a read-only data retrieval tool with a clear name and scope, this is a minor gap rather than a blocking one.

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%: both currency (usd/rmb/sdr) and quarters (default 8, max 40) are fully documented in the input schema. The description adds no parameter-level detail beyond what the schema already states, so the baseline of 3 applies. The cadence and sign-convention information concerns the data itself rather than the parameters.

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 identifies a specific resource — China's quarterly balance of payments (国际收支平衡表) from SAFE's English site — and enumerates the exact data components (current account, capital/financial account, reserve-assets change, net errors and omissions). This content-level specificity clearly distinguishes it from siblings like china_external_debt and china_fx_reserves, which cover different datasets. The BPM6 and quarterly indicators make the scope unambiguous.

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 description gives clear contextual signals about when results are expected (quarterly cadence, ~3-month lag, with a concrete verification date), which helps an agent decide whether the data is current. However, it never explicitly states when to prefer this tool over china_external_debt, china_fx_reserves, or china_safe_releases, nor does it state exclusion conditions. Differentiation is left to inference from sibling names rather than spelled out in the description.

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