knowledge_search

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description is minimal and discloses only that retrieval can be keyword, semantic, or hybrid. It does not disclose return format, whether results include relevance scores, what the 'refresh' parameter does behaviorally, or any side effects (e.g., whether refresh triggers reindexing). For a read/search operation, the minimal disclosure is somewhat adequate but leaves the refresh semantics unexplained.

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 efficient sentence that front-loads the core purpose. It contains zero waste and states the three modes compactly. It could arguably add more detail, but for what it includes, it's appropriately sized.

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?

While an output schema exists, the description covers only a basic search listing scenario. The opaque refresh parameter, the lack of guidance across a suite of many sibling tools (email_*, knowledge_*, vector_*), and the absence of behavioral context around search modes make this incomplete. Given 5 parameters and a large sibling toolset, the description needs more content to be fully navigable.

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 0%, so the description must compensate but does not. None of the 5 parameters are explained in the description. The 'refresh' parameter is particularly opaque — a search tool with a refresh boolean needs explanation of what it refreshes. The 'mode' param has an enum in the schema, but the description names the three modes without explaining differences. Parameters like account_id, limit, and query are self-evident, but refresh is not, and the description adds zero parameter-level meaning.

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 specific verb+resource ('Search the local knowledge corpus') and names the three retrieval modes (keyword, semantic, hybrid). It's clear about what the tool does, but doesn't explicitly differentiate from sibling tools like knowledge_get or vector_search, which appear to be related knowledge-corpus operations. The verb and resource are specific, but sibling context is not addressed.

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 no guidance on when to use this tool vs alternatives. It doesn't mention that knowledge_get exists for retrieving specific documents, or how this differs from vector_search. No context is given for which mode scenarios warrant keyword vs semantic vs hybrid retrieval. The 'local knowledge corpus' scope is implied but not contrasted against sibling tools.

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