search_chunks

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

With no annotations, the description carries the behavioral burden, and it discloses that the operation is semantic, filterable by metadata, and produces embedding and rerank scores. It does not overstate side effects; search implies a read operation. It could add detail on how filters and scores interact, but the core behavior is clearly conveyed.

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?

A single dense sentence that leads with the action and target and ends with scoring detail. There is no filler or repetition of schema field titles.

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?

The presence of an output schema covers return values, but the description still leaves parameter semantics and the relationship to search_documents implicit. For a straightforward search operation the description is adequate, yet it has clear gaps around top_k/min_score and when to use this tool.

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 for five otherwise undocumented parameters. Only 'metadata filters' maps directly to a parameter; kb/query semantics are implicit, and top_k/min_score are not explained at all.

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 names a specific verb ('search'), resource ('chunk bodies of a kb'), and retrieval type ('semantic'), with metadata filtering noted. This clearly distinguishes it from sibling search_documents, which operates at document level.

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 phrase 'semantic search over chunk bodies' implies this is the right tool when an agent needs similarity-based retrieval over chunks, in contrast to sibling document-level tools. However, it never explicitly states when to prefer this tool over search_documents or when not to use it, so usage guidance is only implied.

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