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

Annotations already declare read-only, idempotent, closed-world, non-destructive, so the bar is lower; the description still adds real behavioral context: hard 50-record cap, accompanying dataset status in the response, explicit unverified fields, and the activation-only data boundary.

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?

Dense but front-loaded: purpose first, then filter semantics, then limits and caveats. Every clause carries information, though the long compound sentences could be split for faster scanning.

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 usefully states that results are capped and include dataset status; with only one documented parameter it compensates well elsewhere. The unaddressed offset parameter is the main remaining gap for a 5-parameter tool.

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 only 20% (only category documented), so the description must compensate and largely does: keyword matching covers both English and Chinese names, category accepts the English coverage name or Chinese alias case-insensitively, market is explicitly a sales-market label, and a 50-record ceiling is stated. Offset is the one parameter left unexplained.

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 and resource (search merchant records in an activated public dataset) plus the concrete query dimensions: text, category, and sales-market label. It also carves out that market is a sales-market label, not a business-location filter, which prevents a common misread.

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?

Gives useful scope conditions — only activated public records, no private database, no live crawling, unverified size/use/intent — so the agent knows what data is valid. However, it never states when to prefer this over siblings like get_merchant or get_data_coverage, and the coverage dependency is only implied through the category parameter.

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