Проверить поиск по базе

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

Without relying on annotations, it discloses two non-obvious traits: an empty-but-errorless response when the base is disabled or vectors are not computed, and that the call invokes an external AI service, records expense, and may be billed separately. This explains the otherwise surprising readOnlyHint=false / openWorldHint=true annotation pair.

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?

Four compact sentences with the purpose front-loaded, followed by the verification use case and then the operational caveats. Each sentence carries information, though the billing note could be folded more tightly.

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 retrieval-preview tool with no output schema, the description covers the return nature ('which fragments'), the failure mode, the external-service dependency, and cost implications. It is essentially complete, with only a slightly richer description of the response shape missing.

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 100%, so base, case, limit, and question are all documented in the schema itself (including the case default resolution and limit default of 4). The description adds no syntax or format detail beyond what the schema already provides, so the baseline of 3 applies.

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 and resource: it shows which fragments the base will insert into the model's response for a given question. This clearly distinguishes it from siblings such as knowledge_save, knowledge_add_document, knowledge_reindex, and knowledge_document, which manage or index content rather than preview retrieval.

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?

It gives an explicit usage context: 'Так проверяют, что материалы разобраны и порог близости выбран верно' (this is how you verify materials are parsed and the similarity threshold is set correctly). That is a solid when-to-use, though no alternative sibling is named and no when-not-to-use condition is given.

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