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

Annotations already declare this a safe, closed-world read. The description adds genuinely useful context beyond them: the dataset is NYC-scoped, finite (4,389+ listings), and Chinese-language oriented. It does not disclose pagination behavior or how many results are reachable via page/limit, so the added value is moderate rather than rich.

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?

A single front-loaded sentence with the scope and the two search modes; nothing is wasted or buried.

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 an output schema and safety annotations present, the description needn't explain return values. However, for a paginated search tool it leaves pagination semantics and the q/cat interaction undescribed, which are the main remaining unknowns.

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 50%: q and cat are documented in the schema, while page and limit have no descriptions anywhere. The description reinforces that searching is by keyword or category but says nothing about pagination depth, the 50-result limit, or defaults, so it does not compensate for the gap.

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 gives a specific verb and resource ('Search ... NYC Chinese business listings') plus the two search axes (keyword or category) and a dataset size, so the agent knows exactly what domain this covers. No sibling tool (weather, visa_info, market_quote, etc.) overlaps, so explicit differentiation isn't needed, but it also isn't stated.

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?

'by keyword or category' hints at which parameter to use, but there is no guidance on when to pick this tool over doing something else, no prerequisites, and no note on whether keyword and category can be combined or which wins.

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