semantic_search_instructions

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

No annotations are provided, so the description carries the full transparency burden. It discloses the underlying algorithm (TF-IDF + cosine similarity) and the semantic-matching behavior with an example. However, it does not explain score semantics, result ranking, or limitations (e.g., whether it searches full text or titles), leaving some behavioral aspects unspecified.

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 long, front-loads the verb and resource, and includes a concrete example. Every sentence contributes useful information with no filler.

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?

For a search tool with three parameters and no output schema, the description explains the search scope and algorithm but stops short of describing the return format or ranking. The example and parameter schema cover most essentials, but the absence of output details leaves a moderate gap.

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?

The input schema has 100% description coverage for all three parameters, so baseline is 3. The description adds a natural-language query example, but it does not provide additional meaning for limit or min_score that isn't already in the schema. Therefore, no added value beyond the structured fields.

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 performs semantic search over 1C.BIT instructions using TF-IDF and cosine similarity, and explicitly contrasts it with keyword search ('лучше, чем keyword-поиск'). It provides a concrete example, making its purpose unambiguous.

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 preferred use for natural-language/semantic queries ('Понимает смысловые запросы лучше, чем keyword-поиск'), which distinguishes from the sibling search_instructions tool. However, it does not explicitly name the alternative tool or state when to avoid this tool, so the guidance is clear but not fully explicit.

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