kb_search

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

No annotations are present, so the description carries the full burden. It discloses the hard MISSING_FILTER constraint, that results are truncated summaries rather than full text, that feishu_stub_only/has_fulltext=false does not mean the document is missing, and that kb_get_doc will explicitly refuse to return full text. This goes well beyond what the schema conveys.

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 structured as short labelled blocks, each adding a distinct operational fact: hard constraint, sibling distinction, parameter sourcing, display modes, collection values, and Feishu stub handling. It is dense but every sentence earns its place and it is front-loaded with purpose.

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 search tool with no annotations, the description covers the essential invocation context: minimum filter requirements, error behavior, how to obtain tag names/doc_ids, display truncation, collection enum, and the Feishu stub edge case. Output schema exists, so describing return shape is not needed. Minor omissions like tag_mode and date format prevent it from being perfect, but it is operationally complete.

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 0%, so the description must add semantics. It explains the at-least-one-filter hard constraint, display_mode character counts (compact=80/brief=220/full=400), and collection allowed values (sop/replay/training/talk/internal). However, it leaves tag_mode, date format for created_from/created_to, and pagination semantics undocumented, so compensation is strong but not complete.

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?

Description opens with '知识检索·万能口' and states it filters catalogued documents by keyword/tag/collection/time/quality. It explicitly distinguishes itself from kb_get_doc by noting this tool only returns lists and truncated summaries, not full text. This is a specific verb+resource with clear sibling differentiation.

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 gives an explicit 'when not to use' rule: if a specific section or full body is needed, use kb_get_outline / kb_get_doc. It also frames the difference from kb_get_doc and tells agents to call kb_get_doc when actual full text is needed. This is explicit condition-based routing.

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