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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real behavioral context beyond that: keyless access, live sourcing from NBS via Eastmoney, a 24-month history cap, and the prior-period=100 index convention with a worked example (97.7 = 2.3% YoY fall). It does not describe failure modes or data-refresh lag.

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?

Front-loaded with the resource and the index convention, and the parameter modes are spelled out compactly. The single dense paragraph mixes naming, semantics, and sourcing, which makes it slightly heavier than necessary, but each sentence carries information.

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 supplies the critical decoding rule (prior period = 100) so returned numbers are interpretable, plus the units, geography, source, and history depth. An agent has everything needed to call this correctly and explain results.

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 baseline is 3. The description still adds value beyond the schema by stating the 24-month history window for `city` and by explaining how the two parameters interact (both omitted yields the 70-city cross-section), plus giving a month format example.

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?

Names a specific resource (NBS 70-city residential price indexes), enumerates both index families (new-build 新建商品住宅 and resale 二手住宅) and both comparison bases (YoY, MoM). An agent can immediately distinguish this from sibling macro tools like china_lpr or china_macro_indicator.

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?

Explicitly states the three calling modes: pass city for a city history, pass month to pin a release, pass neither for the full latest cross-section. Also grounds usage in concrete question shapes ("Beijing home price index", "which Chinese cities have falling house prices"). It does not name a sibling as the alternative for macro-rate questions, so it stops short of full routing guidance.

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