Skip to main content
Glama

Умный отчёт

generate_ai_report
Destructive

Строит AI-отчёт по ответам опроса. Отчёт состоит из трёх независимых разделов — текстовый анализ, сравнительный и количественный, — и каждый можно строить отдельно: перебирать формулировки в текстовом, не пересобирая остальное. Работа идёт в очереди: инструмент сообщает, что раздел поставлен в работу, а готовый текст забирает get_ai_report. Повторный запуск того же раздела, пока он строится, ничего не ломает. Тариф ограничивает число опросов с отчётом; пересборка уже существующего отчёта лимит не расходует.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "quiz_id": "<quiz_id>"
    },
    "name": "generate_ai_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
localeNoЯзык отчёта. По умолчанию берётся язык владельца ключа.
quiz_idYesID опроса.
sectionNoКакой раздел построить: all — все три (по умолчанию), text_analysis — текстовый анализ, comparative — сравнительный, quantitative — количественный.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing that work is asynchronous and queued, that the call only acknowledges placement rather than returning the text, and that tariff quotas apply only to new surveys, not rebuilds. It does not explicitly say what happens to the previous report content when a section is regenerated, which matters given destructiveHint=true; the phrase 'пересборка уже существующего отчёта' only implies overwrite.

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

Conciseness4/5

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

The first sentence front-loads the purpose and the rest layers behavior, queue semantics, and quota rules in a logical order. The clause about iterating wording in the text section partially restates the preceding independence claim, so there is minor redundancy, but no filler.

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

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an async generator with no output schema, the description covers what the call returns (a queued acknowledgement), how to obtain the result (get_ai_report), idempotency of in-flight re-runs, and quota implications. The main remaining gap is the fate of existing report content on rebuild, which is not stated despite destructiveHint=true.

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

Parameters3/5

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

Schema coverage is 100%, so all three parameters including the section enum are already documented in the schema. The description adds the meaningful idea that sections are independent and individually rebuildable, which informs how to use 'section', but it says nothing extra about 'locale' or the quiz_id scoping. Baseline 3 is appropriate when the schema carries the parameter detail.

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

Purpose5/5

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

States a specific verb+resource ('Строит AI-отчёт по ответам опроса') and immediately decomposes the resource into three named sections (текстовый анализ, сравнительный, количественный). It also names the sibling that retrieves the result (get_ai_report), so an agent can distinguish generation from retrieval without opening another schema.

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

Usage Guidelines5/5

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

Explicitly says each section can be built separately and that wording can be iterated in the text section without rebuilding the rest, which is the core usage decision. It names the alternative (get_ai_report) for the follow-up step and spells out two edge conditions: re-running a section while it is in progress is harmless, and rebuilding an existing report does not consume the plan limit. Little is left to inference.

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