Skip to main content
Glama
Sign In

Ruforge

by ru.ruforge.lk
OverviewDiscussionsAdmin

Начать диагностику

ruforge_diagnostic_start

ОСНОВНОЙ способ пройти диагностику RuForge прямо в чате: создаёт сессию (адаптивный режим, как на сайте: ~25 вопросов, точное число зависит от ответов) и возвращает ПЕРВЫЙ вопрос. Правила ведения: задавайте строго ОДИН вопрос за сообщение — заголовок «Вопрос N из ~25 · Компетенция» (берите поле progress), период (если есть), текст ситуации и варианты списком A/B/C/D без комментариев и подсказок; затем ждите ответ пользователя. Не выбирайте за пользователя и не объединяйте вопросы. Перед стартом спросите роль (размер компании и число прямых подчинённых — по желанию). Дальше — ruforge_diagnostic_answer на каждый ответ, в конце — ruforge_diagnostic_finish.

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": {
      "role": "<role>"
    },
    "name": "ruforge_diagnostic_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoadaptive (по умолчанию, ~25 вопросов, как на сайте) или classic (фиксированные 33)
roleYesentrepreneur — предприниматель/собственник; c_level — CEO/COO/CFO; product — руководитель продукта; dept_head — руководитель отдела/функции; division_head — руководитель направления/дивизиона
sourceNoНазвание ассистента для аналитики (utm_source), по умолчанию mcp
access_tokenNoaccess_token из ruforge_profile_check / ruforge_profile_confirm, если пользователь подтвердил e-mail — результат попадёт в историю профиля
company_sizeNoРазмер компании (сотрудников), по умолчанию 50-500
direct_reportsNoПрямых подчинённых, по умолчанию 1-5
respondent_nameNoИмя (необязательно; попадает только в отчёт пользователя)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / access_token
      Added value: +{
+  "description": "access_token из ruforge_profile_check / ruforge_profile_confirm, если пользователь подтвердил e-mail — результат попадёт в историю профиля",
+  "type": "string"
+}
    • removedInput schema / properties / user_id
      Removed value: -{
-  "description": "ID профиля RuForge (из ruforge_profile_confirm), если пользователь авторизован — результат попадёт в историю профиля",
-  "type": "string"
-}
  2. Changed1 schema field changed
    • addedInput schema / properties / user_id
      Added value: +{
+  "description": "ID профиля RuForge (из ruforge_profile_confirm), если пользователь авторизован — результат попадёт в историю профиля",
+  "type": "string"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / mode
      Added value: +{
+  "description": "adaptive (по умолчанию, ~25 вопросов, как на сайте) или classic (фиксированные 33)",
+  "enum": [
+    "adaptive",
+    "classic"
+  ],
+  "type": "string"
+}
  4. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-idempotent, closed-world creation, and the description is consistent with that while adding real context: session length varies with answers, the call returns the first question, and a progress field drives the displayed header. It does not cover failure modes (e.g. invalid role) or whether the session persists server-side, keeping it below a 5.

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?

Front-loaded with the core action and return value, then the operating rules. The paragraph is dense with semicolon-chained instructions and could be split into a short 'what' sentence plus a 'how' block, but nearly every clause is operationally necessary.

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

Completeness5/5

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

Even though there is no output schema, the description explains that a session is created and the first question is returned with a progress field, and it links forward to the answer/finish siblings. Nothing an agent needs in order to start and conduct the diagnostic is missing.

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 100% so the baseline is 3; the description adds value by telling the agent to elicit role/company_size/direct_reports from the user before calling and by noting these contextual fields are optional. It does not add syntax or defaults beyond what the schema already documents.

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: creates a diagnostic session (adaptive, ~25 questions) and returns the FIRST question. It explicitly positions itself as the entry point versus ruforge_diagnostic_answer and ruforge_diagnostic_finish, so an agent can distinguish it from siblings without opening schemas.

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?

Gives explicit sequencing: ask the user's role (optionally company size / direct reports) before starting, then call this tool, then ruforge_diagnostic_answer for every answer, ending with ruforge_diagnostic_finish. It also states what NOT to do — do not answer for the user, do not merge questions, strictly one question per message.

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

All Ruforge toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources