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

readOnlyHint=true already tells the agent this is a safe read, so the description's burden is lighter. It adds useful behavioral context — the directory is limited to six cities, filters are combinable, and subsidy specifics live behind get_park — but it does not describe result shape, ordering, or how paging behaves in practice.

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?

Three short bracketed blocks with the core purpose first and the recommended usage and drill-down partner after. The 【杀手用法】 framing is slightly promotional, but it front-loads the most actionable guidance and nothing is redundant.

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?

For a 7-parameter, read-only directory listing with no output schema, the description covers what the tool returns (park records from a six-city catalog), how to narrow it, and where to go for deeper per-park detail. Pagination nuances are the only gap and are documented in the schema.

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 a 3 would be the floor; the description earns above that by stating that filters stack and by calling out the single most common filter value (RENT_SUBSIDY) as the recommended entry point. It does not add syntax or semantics for q, cursor, or limit beyond the schema.

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?

"浏览/筛选 OPC 园区目录(六城)" gives a specific verb (browse/filter) plus a specific resource (OPC park directory) and scopes it to six cities. It also explicitly distinguishes itself from the sibling get_park, which is the drill-down rather than the listing.

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 names the highest-value invocation pattern (benefitType=RENT_SUBSIDY for parks with rent subsidy) and states which filters can be stacked (city/track/status/keyword). It also routes detail-seeking queries to get_park instead, so the boundary between listing and lookup is explicit.

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