Создать или настроить базу знаний

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

Annotations already say readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true, so the mutation nature is declared. The description adds meaningful behavioral constraints not captured in the machine-readable annotations: created vs updated behavior depending on `base`, the empty-base restriction for changing/removing provider because vectors from different models are incompatible, and the need to rebuild chunks after changing chunk size via knowledge_reindex. No contradiction between description and annotations.

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: three sentences, each carrying important operational information. It front-loads the primary create/update distinction, then adds the critical constraints. 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?

Given 10 parameters, 100% schema coverage, an output schema absent, and annotation hints present, the description is reasonably complete. It tells the agent the key conditional behavior, the vector-service requirement, the empty-base restriction, and the reindex follow-up. A minor gap: it doesn't explain what happens regarding the `active` flag or defaults, but those are covered by the schema. The open-world hint and no required parameters align with the flexible create-or-update nature.

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 schema descriptions already cover 100% of parameters, so the baseline is 3. The description adds value by explaining the crucial conditional behavior of `base` (omit to create, specify to update), which is not fully captured by the parameter description alone, and by relating `provider` to the vector-service requirement and `chunk_size` to the reindex action. However, it doesn't describe each parameter individually; the schema does that.

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 a specific action: with no `base` parameter it creates a knowledge base, with `base` it modifies its settings. This distinguishes it from sibling knowledge tools like knowledge_list, knowledge_reindex, knowledge_search, knowledge_delete, and knowledge_add_document. The verb is explicit ('создаёт', 'меняет') and the resource (base of knowledge) is named.

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 explicitly explains when to use it without `base` (create) versus with `base` (configure), and it references the sibling `knowledge_reindex` for the case when chunk_size is changed. It also gives conditions: provider can be changed or removed only on an empty base, and the AI-vector-service connection requirement for search. This is clear enough for an agent to select this tool and avoid mistakes.

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