corpus_stats

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

With no annotations provided, the description carries the full burden of disclosure. It does usefully enumerate the returned metrics (total count, time range, source distribution, pending/failed counts, site totals), which tells the agent what data to expect. However, it does not state whether the operation is read-only vs. side-effectful, nor does it clarify the meaning of 待抓取/失败 (pending/failed) which implies crawling activity that may relate to update_corpus.

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 with the core concept (语料库覆盖情况) front-loaded, followed by a concrete metric enumeration. It is efficient with no filler. Slightly dense without grouping or punctuation breaks between the five listed items, but appropriately sized for a parameterless stats tool.

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 zero-parameter tool with no output schema, the description provides sufficient coverage: it enumerates exactly what statistics the agent will receive. The main weaknesses are the vague '对比' and the unexplained pending/failed statuses, which would benefit from a note that this reflects background crawler state, but overall the agent can decide to call it 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 tool has zero parameters and an empty input schema, so the baseline of 4 applies. There is no parameter meaning the description needs to add, and the lack of argument documentation is not a gap here.

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 states a clear purpose: reporting corpus coverage (总篇数/time range/来源分布/待抓取-失败数/站点总数). It names the resource (corpus) and a specific set of metrics, distinguishing it from retrieval tools like list_articles, search, and get_article, which return article-level data rather than aggregate statistics. It loses a point because the trailing '对比' (comparison) is vague about what baseline the site totals are compared against.

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?

No guidance is given on when to use this tool versus alternatives. It does not explicitly frame itself as the corpus-level overview choice, nor does it mention that list_articles or search are for specific article retrieval. The metric list implies an analytics use case, but the agent must infer this rather than being told.

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