Skip to main content
Glama

dn_ask

Вопрос о компаниях/рынке/сегменте или structured JSON. Рецепт экономии контекста LLM: • Сегмент >20: preview_only=true → total без списания; list — structured_only + fields_preset=leadgen. • Постраничный list: первая страница — fields_preset (leadgen/full); далее только continuation_token (без другого fields_preset — иначе срежется набор полей токена). • Карточки/batch_cards: structured_only + fields_preset=full. Биллинг: preview/validation=0; list=N карточек; continuation не идемпотентен. При continuation_token — повторить dn_ask с тем же токеном. При need_structured — скопировать draft_*_json из applied_filters. Полный DTO секции → dn_get_section; событие рынка → dn_get_event.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "dn_ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
innNoИНН, если известен
ogrnNoОГРН, если известен
fieldsNoСписок блоков data[] (приоритетнее fields_preset)
formatNostructured_only (default MCP) | json | markdownstructured_only
localeNoru
questionNoТекст вопроса (опционально при structured-входе)
list_limitNoЛимит 1–20
list_offsetNoСмещение (не с continuation_token)
preview_onlyNoТолько счётчик сегмента, 0 токенов
fields_presetNoПроекция data[]: full | minimal | leadgen | finance | risk
idempotency_keyNoКлюч идемпотентности: повтор с тем же телом не списывает токены (24ч)
include_payloadNotrue — полный company_sections.payload в ответе (иначе has_payload)
market_registryNocontracts|leases|vacancies|court|products|arbitration|arbitration_stat
company_ops_jsonNoJSON: inn/ogrn + operations[]
dictionary_queryNoJSON: name + search
misc_request_jsonNoJSON: kind + request
continuation_tokenNoТокен следующей страницы
market_filter_jsonNoJSON тела market-запроса
segment_filters_jsonNoJSON-фильтр сегмента (snake_case; можно вставить черновик из ответа NL)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / fields / description
      Previous value: -"Allowlist блоков data[] (приоритетнее fields_preset)"New value: +"Список блоков data[] (приоритетнее fields_preset)"
    • changedInput schema / properties / preview_only / description
      Previous value: -"Только count сегмента (filtersPreview), 0 токенов"New value: +"Только счётчик сегмента, 0 токенов"
    • changedInput schema / properties / segment_filters_json / description
      Previous value: -"JSON GetCompaniesBatchRequest (полный сегмент; можно вставить черновик из ответа NL)"New value: +"JSON-фильтр сегмента (snake_case; можно вставить черновик из ответа NL)"
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavior: billing is preview/validation=0, list charges N cards, continuation is explicitly non-idempotent, and idempotency is bounded to 24h via the same body. It also describes recovery behavior (retry dn_ask with the same continuation_token, and copy draft_*_json from applied_filters when need_structured), which is genuinely operational. Auth requirements, error modes and response shape beyond applied_filters/company_sections are not covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, then billing/pagination recipes are grouped in scannable bullets, and the final sentence handles escalation to sibling tools. The abbreviated telegraphic style is dense, but every clause carries operational information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

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 escalation well but leaves a large semantic hole: an agent cannot tell from it which of the many JSON parameters selects which mode, nor what the response envelope looks like beyond applied_filters and company_sections. It is adequate for the list/preview path but incomplete for the structured-JSON paths.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 95%, so the baseline is 3; the description earns a bump by documenting cross-parameter interaction the schema does not, notably that changing fields_preset mid-pagination truncates the token's field set and that preview_only suppresses billing. It still leaves the many JSON-blob parameters (market_filter_json, segment_filters_json, company_ops_json, misc_request_json) without describing their internal shape.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening line states the resource broadly ("Вопрос о компаниях/рынке/сегменте или structured JSON"), which tells an agent it is a question/query dispatcher, but it never names the verb precisely nor clarifies how the many modes (market_registry, dictionary_query, misc_request_json, company_ops_json) relate to that purpose. Sibling differentiation appears only as trailing routing hints to dn_get_section and dn_get_event.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete when-to guidance for the main paths: preview_only=true for segments over 20 to get a total without spending tokens, list via structured_only + fields_preset=leadgen, first page carries fields_preset while later pages use only continuation_token, and cards/batch_cards use fields_preset=full. It also routes full DTO to dn_get_section and market events to dn_get_event. Gaps remain for the JSON-mode parameters (dictionary_query, misc_request_json, company_ops_json), where no selection guidance is offered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources