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

Beyond the openWorldHint annotation, the description adds significant behavioral context: it covers specific POI types, explicitly states it does not answer count questions, clarifies that pricing is per data unit (region × POI type) not per POI row, and requires explicit region names. It does not disclose potential error conditions or rate limits, but the given annotations are minimal and the description carries substantial burden that it satisfies.

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 front-loaded with the core purpose, then covers exclusions and alternative tools, followed by typical queries and pricing. It is somewhat lengthy but every sentence adds useful information. The structure is logical and avoids redundancy, though the pricing detail could be considered extraneous.

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?

Given the tool has an output schema (so return format is defined), the description adequately covers what the tool does, its limitations, and cost model. It mentions the covered POI types and what it does not do, and provides typical usage examples. It could mention edge cases like invalid region names, but overall it is complete enough for an agent to select and use correctly.

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 parameters are well documented. The description adds value by giving example query phrasings, explaining that gov_name and poi_type can be inferred from input_text when omitted, and clarifying the billing unit (one region × one POI type). This goes beyond the schema's basic descriptions.

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 clearly states the tool queries detailed lists of transportation POIs (airports, train stations, subway stations, bus stops, parking lots) within a specified administrative region. It explicitly distinguishes itself from siblings by stating it does not answer count statistics and directs users to gov_data_poi_amenity for counts and gov_data_transport for speed/capacity metrics, matching the purpose with other poi_data_* tools.

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 provides explicit usage guidance: requires a clear city or district name, typical query patterns are given ('某区地铁站分布、有哪些火车站、公交站列表'), and it explicitly states when not to use this tool (for counts or traffic metrics) and names the alternative tools (gov_data_poi_amenity, gov_data_transport). This gives clear when-to-use and when-not-to-use instructions.

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