ingest_passage

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

With no annotations, the description carries the full burden, and it delivers meaningful behavior: the engine validates number continuity, legal tags, and answer-key consistency, and rejects bad input ("有问题会退回"). It also discloses that web-sourced keys get flagged as "未核对答案册" in results. It stops short of describing idempotency (what happens when the same source is ingested twice) or the shape of rejection feedback.

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 simplest call shape is front-loaded, then progressively richer alternatives follow, which matches how an agent should decide. Sentences are dense but each carries a distinct fact; the middle clause about web lookup and *_origin flags is the only slightly tangled segment.

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 13-parameter, nested, mutation-style ingestion tool with no annotations and no output schema, the description covers what an agent needs before calling: which combinations of inputs are valid, the validation-and-rejection contract, the provenance labeling, and the no-grading boundary. Minor parameters like reflections and elapsed_minutes are self-described in the schema and don't block correct invocation.

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 already 77%, so the baseline is high, yet the description still adds value: it shows the literal answer_sheet format with a worked example ("1 FALSE NG / 2 two weeks | two week / 3 B ✓") that the schema does not spell out, and it explains that questions_text propagates instruction/word-limit lines to subsequent questions. The remaining parameters (reflections, elapsed_minutes, answer_line vs user_answers) are left to 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 opening sentence gives a specific verb and resource ("录入一篇阅读或一个听力 Part" — ingest a reading passage or listening Part). The closing "不判题" (does not grade) implicitly separates it from judge_set, but no sibling is named outright, so the differentiation is by implication rather than explicit.

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 enumerates the input pathways and the condition that selects each: source + answer_sheet is called the easiest path, questions_text and passage are optional add-ons, structured questions are an alternative, and set_id is the reuse path when the set already exists. It also specifies the condition for the web fallback ("用户没给原文/答案时"), so an agent can choose a route without guessing.

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