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

The description discloses key behavioral traits: data is 'checked against official sources and dated', indicating reliability and currency. It notes that ticket channels are 'official (no resellers)', which is a specific honesty indicator. With no annotations provided, the description carries the full burden, and it does so well by describing the source quality and exclusions. However, it doesn't mention whether the data is cached, how often it's updated, or what happens for unsupported cities, which would provide even fuller transparency.

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 a single, focused paragraph with front-loaded purpose and detailed examples. Every sentence adds distinct value: the first sentence defines scope, the middle lists key data categories, and the last provides usage examples. No wasted words. It is efficient and easy for an AI to parse quickly.

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 only one parameter (city), no output schema, and no annotations, the description is remarkably complete. It covers the input parameter clearly, explains what data will be returned (with sufficient detail for an agent to judge relevance), and gives example queries. The sibling context makes its role in the tool ecosystem clear. There is no missing information that would prevent correct invocation or interpretation.

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?

The only parameter is 'city' with complete schema coverage. The description adds significant value beyond the schema by explaining what 'city' represents (a Chinese city for foreign traveler facts), giving examples ('"Beijing" or "lhasa"'), and showing how it's used in queries. The schema's description was brief, so the tool's description compensates richly. A small deduction for not explicitly saying the slug can be in Chinese characters (if applicable) or clarifying boundary cases.

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 what the tool does with a specific verb ('Facts') and resource ('a Chinese city'). It lists the exact categories of information provided (attractions, tickets, hotels, payment) and who it's for (foreign travelers). This distinguishes it effectively from siblings like 'check_attraction_booking' and 'check_transit_eligibility', which are narrower in scope.

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 explicitly tells when to use this tool: for questions like 'how do I book X in <city>' or 'can foreigners stay in hotels in <city>'. It also contrasts with siblings implicitly by covering a broad set of travel needs rather than a single check. The guidance is concrete and actionable for an AI agent deciding between tools.

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