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

Annotations already declare readOnly/idempotent/non-destructive and open-world, so the safety profile is covered. The description adds genuinely useful context: keyless access, live sourcing from CFETS/NIFC, the 11:00 Beijing fixing timing, and history depth limits. It does not describe response shape or failure modes, but with annotations carrying the heavy lifting this is solid added value.

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 content is front-loaded and organized by `series` value, which is good. However, sentences are dense with parentheticals ("the dated 1-year/10-year benchmark series (IMF SDDS disclosure)") and some detail (IMF SDDS, NIFC naming) may matter to few agents; a 4 rather than a 5.

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?

With no output schema, the description carries the burden of telling the agent what comes back, and it does: 8 SHIBOR tenors from overnight to 1-year, the dated 1Y/10Y CGB benchmarks, and the full real-time quoted curve. Freshness (11:00 Beijing fixing), sourcing, and history limits round it out, so nothing essential for correct invocation 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 all three parameters are already documented, including the shibor-only and yield_curve-only scoping. The description reinforces the semantics (up to `days` of daily history, all 8 tenors, ~1 month to ~50 years maturity range) but adds little beyond the schema text. Baseline 3 holds.

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 resource (China money-market and government-bond benchmark rates) and explains the two modes precisely: shibor across 8 tenors, yield_curve with 1Y/10Y benchmarks plus CFETS quoted curve. An agent can distinguish both output shapes without opening the schema, and the sibling set (china_lpr, china_macro_indicator) is unlikely to be confused with it.

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?

Usage is made concrete through example intents ("current SHIBOR rates", "China's 10-year government bond yield") and by explaining which series answers which question. Missing an explicit exclusion or pointer to sibling tools like china_lpr for policy rates, so it falls short of a 5.

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