zhihu_search_questions

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

Beyond the readOnlyHint annotation, the description discloses that search is fuzzy and may mix dates, that results are sorted by answer count, that visits_count serves as a heat proxy, and that it outputs specific candidates. These details help set expectations about behavior and output.

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 compact yet information-dense: it covers purpose, output structure, two convenience fields, fuzzy matching behavior, and the recommended workflow in just a few sentences. Every sentence earns its place.

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 search tool with no output schema, the description fully specifies the return list fields and the two candidate objects. It also explains the sorting order and the purpose of each key field, making it self-sufficient for an agent to invoke 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?

The description explains that the keyword is a fuzzy search query, that the date parameter filters titles to the exact day, and that limit controls the result count. It adds real-world context (like the example keyword) beyond the schema 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 searches Zhihu questions by keyword, returns a list sorted by answer count, and identifies two key candidates (most_answers and hottest). It also gives a concrete example query, distinguishing it from sibling tools like content retrieval.

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?

It provides explicit guidance: use this tool to locate the day's 'today's market' question, then pass its URL to zhihu_draft_answer. It also warns about fuzzy matching and advises passing a date to filter precisely, giving clear context for when and how to use it.

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