kb.search

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains the two search algorithms (FTS5 and vector similarity) and the condition for using vector mode. It does not discuss side effects, authentication, rate limits, or return format, but the core behavior is well described. A 4 reflects good transparency missing some details like truncation behavior.

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 two sentences plus a tip, all front-loaded with essential information. No extraneous words. The first sentence states purpose and modes, the second provides a valuable usage tip. This is concise and well-structured, earning a 5.

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?

Given the tool's complexity (7 parameters, no output schema, no annotations), the description is incomplete. It does not explain how to use vector search (requires qdrantUrl and qdrantCollection), does not mention the limit parameter, and does not describe the return format or truncation behavior. Important details are missing, making it insufficient for an agent to use correctly without additional context. Score 2.

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 description coverage is low at 29% (only 2 of 7 parameters have descriptions). The description mentions 'vector' but does not explain the other parameters: limit, qdrantUrl, qdrantCollection, project_id, or max_content_length. It adds minimal meaning beyond the schema, which is insufficient given the low coverage. A 2 is appropriate.

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 states the tool searches the knowledge base and specifies two search modes: SQLite FTS5 by default and optional Qdrant vector similarity when a vector is provided. This is a specific verb+resource+modes. While it does not explicitly differentiate from sibling search tools like memory.search or source.search, the 'kb' prefix and mention of 'knowledge base' provide sufficient context. A 4 is appropriate as it is clear but lacks explicit 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 includes a tip to call kb.index first to read the table of contents before searching blind, which provides a usage guideline about a prerequisite. However, it does not explicitly state when to use this tool versus alternatives (e.g., memory.search for semantic search) or when not to use it. This is minimal guidance, earning a 3.

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