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

With no annotations, the description carries the full burden and does well: it discloses billing (preview/validation cost 0, list costs N cards), that continuation is not idempotent and must be replayed with the same token, and that need_structured requires copying draft_*_json from applied_filters. Still missing: error behavior, rate limits, auth, and response shape (e.g. has_payload vs full payload).

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 bulleted layout is front-loaded and most lines carry operational value, but the 'structured_only + leadgen' recommendation is repeated three times and the telegraphic style ('Биллинг: preview/validation=0') makes it harder to parse than necessary. It is dense rather than bloated, but not tight.

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 19-parameter tool with no annotations and no output schema, the description covers billing, pagination, and sibling hand-offs, but says nothing about the four JSON request parameters or the market_registry enum values, which are a major part of the tool's surface. Adequate for the NL path, incomplete for the structured path.

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 95%, so the baseline is 3 and the schema already documents most parameters, including the fields-vs-fields_preset priority that the description repeats. The description adds cross-parameter combinations (format + fields_preset + continuation_token) and the continuation/offset incompatibility, but leaves market_registry, company_ops_json, dictionary_query, and misc_request_json without any usage 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 opening line states the resource (companies/market/segment) and the two input modes (NL question vs structured JSON), and the closing sentence distinguishes it from dn_get_section and dn_get_event. The verb 'ask' is vague and the tool is really a multi-mode router, but an agent can still tell what it is for and where the boundaries with siblings lie.

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 'recipe' block gives concrete when-to-use patterns: preview_only=true for segments over 20 before listing, structured_only + fields_preset=leadgen for paginated lists and card batches, and explicit hand-offs (full section DTO → dn_get_section, market event → dn_get_event). It lacks any explicit 'when not to use' or guidance on the four JSON-mode parameters.

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