interview_questions_bank

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

With no annotations, the description carries the behavioral burden and does well: it discloses that the bank is free, that questions are drawn without answers, and that check returns correctness, the correct answer, and explanation. It does not cover edge cases or rate limits, but the core behavioral contract for an agent is clearly stated.

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 compact sentence that front-loads the resource and then enumerates each action mode in a parallel structure. There is no filler and every clause contributes actionable information.

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?

Although the tool has 8 parameters and no output schema, the description plus rich schema is enough: each action's return behavior is stated (tree, questions without answers, check with explanations), and parameter constraints live in the schema. A small gap is that the description does not explicitly link that questions returns questionId for use by check, but this is inferable.

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 description coverage is 100%, so the baseline is 3; the schema already documents action enums, count limits, company/section examples, and check-required fields. The description adds only a little by mapping '按大类/企业' to section/company, which reinforces but does not significantly extend 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?

The description names the resource (笔试真题库) and breaks the tool into three explicit actions: sections for the category tree, questions for drawing exam questions, and check for grading answers. This makes the tool's purpose unambiguous and clearly distinct from siblings like resume_rewrite or interview_coach.

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 provides clear action-level routing: use sections to browse categories, questions to draw questions by section/company, and check to submit answers for grading. It does not explicitly state when to prefer this tool over sibling tools, but the internal action guidance is sufficient for correct use.

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