semantic_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 states 'Search' which implies read-only, but it does not explicitly declare that it is a read-only operation or mention any side effects, prerequisites beyond indexing, error conditions, or performance implications. The phrase 'indexed local files' hints at a prerequisite but does not outline the full behavioral scope.

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, front-loaded sentence with no filler. Every word adds value, clearly communicating the core functionality, the indexed nature of the files, and the use of Intel NPU embeddings.

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?

Despite having an output schema, the description lacks crucial context: it does not explain the meaning or allowed values of 'root', imply the need for a pre-existing index, or mention error handling. The presence of sibling indexing tools helps but is not leveraged in the description to clarify the intended workflow.

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?

Because schema description coverage is 0%, the description must compensate by explaining parameter semantics. It only adds context about meaning-based search and NPU embeddings, leaving 'root' unexplained and not clarifying the scope or format of 'query' and 'limit' beyond their names and defaults. The parameter names are somewhat self-explanatory, but the description adds minimal value.

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's function: 'Search indexed local files by meaning using Intel NPU embeddings.' It identifies the specific verb (Search), the resource (indexed local files), and the method (meaning-based via NPU embeddings), which distinguishes it from siblings like semantic_index (indexing) and npu_status.

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 implies that files must be indexed before searching ('Search indexed local files') and that the search uses Intel NPU embeddings, but it does not explicitly state when to use this tool over alternatives or provide exclusions. No sibling comparison or prerequisite mention is given, leaving the context implicit.

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