kb_search

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

No annotations are provided, so the description must fully convey behavioral traits. It explains that the tool performs semantic search, supports two languages, and can expand results with graph neighbors, which is useful. However, it does not disclose any side effects, permissions, or safety considerations. Since it is a search tool, read-only behavior is implied, but the lack of explicit confirmation and no annotation coverage prevents a higher score. There is no contradiction with annotations, so this is not a 1.

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 concise and well-structured. It leads with the core purpose, then provides a brief behavior note, and finally lists arguments in a clear format. Every sentence adds value; the argument list is introduced with 'Args:' and each parameter has a short explanation. It is not overly verbose and avoids repetition, earning a 4.

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?

An output schema exists, so return values are already specified. The description covers the main functionality and parameters, but lacks details on edge cases like maximum n_results, how to determine valid doc_type values, or the exact behavior of expand_graph beyond a one-hop expansion. These are not critical given the output schema, but the vagueness around doc_type and expand_graph leaves some gaps. A 3 is appropriate.

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 0% schema description coverage, the description must compensate. It does provide explanations for all four parameters: query with examples, n_results with default, doc_type as a filter, and expand_graph as a boolean. However, doc_type is described vaguely ('depends on your KB schema') without concrete options, and n_results lacks range or constraints. The description adds meaning beyond the schema but does not fully cover all ambiguities, justifying a 3.

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 clearly identifies the tool as performing semantic search over the knowledge base, specifically targeting markdown documents with YAML frontmatter. It adds details about multilingual support (Russian and English), which helps distinguish it from a generic search. However, it does not explicitly name any sibling tools or contrast them, so it earns a 4 rather than a 5.

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 guidance on using parameters such as expand_graph to include knowledge graph neighbors and doc_type for filtering, which is helpful. It implies when the tool should be used (semantic search scenarios) but does not explicitly state when not to use it or mention alternatives like session_search or source_search. The exclusion guidance is absent, limiting the score to 3.

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