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

No annotations exist, so the description carries the full burden and does little: 'полным payload' hints at a heavy response but says nothing about pagination (limit/offset in params), required identifiers, or permissions. A read-only assumption is only inferable from 'get'.

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?

A single front-loaded sentence with no waste, though it is arguably too terse for a 5-parameter tool with nested objects.

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?

With 5 parameters, a nested params object, no annotations, and no output schema, the description is far too thin to call the tool reliably. It omits identifier selection, format behavior, and what the full payload contains.

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 coverage is only 40%, so the description should compensate, but it mentions only 'section' and adds no meaning for inn/ogrn/format/params. The distinction between looking up by INN vs OGRN, and what 'structured_only' format means, is left entirely undocumented.

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 names a specific resource ('одна секция карточки компании') and the retrieval verb, and distinguishes itself from dn_ask by noting it returns the full payload rather than an answer. It stops short of 5 because the term 'секция' is only clarified by the schema, not the prose.

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 a concrete usage condition: call this after dn_ask when has_payload is present. That is real routing guidance an agent can act on, though it does not state when NOT to use it or contrast with dn_get_event.

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