CC98 增强搜索

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds real behavioral context: results are deduped/reranked, snippets come from verified first posts, and coverage is reported as a snapshot rather than an exhaustive index. That tells the agent results are ranked and potentially partial. It does not explain what 'refresh' does or what a 'coverage range' looks like, which keeps it from a 5.

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?

Four short, dense clauses with no filler. The ordering is mildly counterproductive — retrieval-pipeline mechanics lead before the plain statement of what the tool is — but nothing is wasted.

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 tool taking 9 parameters with no output schema and no schema descriptions, this description is well short of what an agent needs: the two main tuning enums are undocumented and the shape of the returned 'snapshot' is only gestured at. An agent could fire a bare keyword call, but could not confidently use most of the optional parameters.

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?

With 9 parameters and 0% schema description coverage, the description must carry parameter meaning, and it explains only one ('terms' corrects Chinese segmentation). The trade-off behind depth's quick/balanced/deep enum is unexplained, as are sort, limit, refresh, board_id, and the created_after/created_before date bounds. That leaves most of the calling surface undocumented.

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 does state what the tool is: a keyword search over CC98 that does multi-path recall, dedup/rerank, first-post verification, and returns hit snippets plus a coverage snapshot. The closing clause 'not full-site full-text search' usefully bounds the scope. It loses a point because the core verb (search) is buried in pipeline jargon, and differentiation from the sibling cc98_search_results is left implicit rather than stated.

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?

'terms 可纠正中文分词' gives one concrete trigger for using a parameter, and '不是全站全文检索' signals an expectation-setting boundary. But there is no guidance on when to prefer this over cc98_search_results, no mention of how to page through the returned snapshot, and no mention of what depth/sort/refresh are for when choosing the call.

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