Создать или настроить базу знаний

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

The description adds meaningful behavioral context beyond annotations: creates vs. updates depending on base, vector incompatibility across models, and the need to rebuild materials after changing chunk_size. These are non-obvious traits not conveyed by readOnlyHint/destructiveHint/idempotentHint annotations. No contradiction with 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?

Three compact sentences, front-loaded with the core create/update distinction, and every sentence carries useful information. No redundancy or fluff.

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?

The description is strong for a mutation tool with 10 parameters and no output schema: it covers create/update behavior, prerequisites, provider-change constraints, and post-update reindexing. It doesn't mention return value or all defaults, but the schema covers most parameter details, leaving only minor gaps.

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 already covers all 10 parameters with descriptions (100% coverage), so baseline is 3. The description adds value by explaining behavioral consequences for base (create vs. update), provider (only changeable when empty), and chunk_size (requires reindex), going beyond the schemas' field-level semantics.

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 dual purpose: without the base parameter it creates a knowledge base, with the parameter it changes settings. It explicitly names the resource ('базу') and distinguishes behavior based on the base parameter, while also pointing to knowledge_reindex as a related sibling.

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 provides explicit when-to-use guidance: create vs. update based on presence of base parameter, and states a key prerequisite (AI service for vectorization). It also gives a constraint (provider change only on empty base) and a follow-up action (reindex after chunk_size change), naming the alternative tool knowledge_reindex.

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