semantic_search

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

With no annotations, the description carries the behavioral disclosure burden. It transparently explains the optional reranker, the unbounded logit nature of rerank_score, and the time tradeoff. It does not cover the full return structure, but the output schema fills that gap.

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 compact and front-loaded: the purpose is in the first sentence, followed by a caveat paragraph that adds behavioral nuance. No sentence is wasted.

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 presence of an output schema, the lack of annotations, and moderate complexity, the description covers the core purpose, a key behavioral caveat, and an implicit prerequisite. It could add more detail about root and limit, but overall it is sufficiently complete for selection and initial invocation.

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. It provides rich semantics for the rerank parameter (what rerank_score is, how to disable it), but leaves root and limit unexplained beyond their names; query is implied by 'search'.

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 opens with a specific verb and object: 'Search indexed local files by meaning using Intel NPU embeddings.' This clearly distinguishes the tool from siblings like semantic_index and semantic_index_status, and states the method of search.

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 'indexed local files' implies the tool is used after indexing and for semantic rather than keyword search. It also provides conditional guidance for reranking ('Pass rerank=false to skip the extra second of work'), though it doesn't explicitly name alternative tools for exclusion.

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