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

Annotations already declare read-only, idempotent, non-destructive, open-world. The description adds the valuable behavioral fact that omitting the filter broadens to the full set, and lists what each record contains. It does not discuss volume, pagination, or freshness of policy data.

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 field list, then a bracketed usage section, then the default behavior. No filler; every sentence carries an actionable fact.

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?

A simple one-param read tool with no output schema, yet the description enumerates the returned record shape, which is exactly what's missing from structured data. Minor gap: no coverage of result size or how city/district strings are matched.

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 single parameter is already documented as a city filter. The description's sentence '不传 city 返回全部' restates the schema rather than adding semantics like accepted city/district name formats.

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 verb+resource (list city/regional startup policy dividends) and enumerates the returned fields (title / issuing body / date / highlights / source). It is clearly distinct from park- and stats-oriented siblings like list_park_city_stats or list_park_news.

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?

Explicit 《when to use》 section with two concrete utterance examples (「深圳 OPC 有什么政策红利」「入驻前看看当地政策」) plus the rule that omitting city returns all. Nothing 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.