Skip to main content
Glama

create_article

Создать новую статью. Короткую статью можно создать сразу со всеми блоками в body. ВАЖНО для длинных статей: не передавай весь текст в body одним вызовом — большой body может оборваться по длине ответа модели, и тогда вызов придёт без обязательного поля name (ошибка валидации). Надёжный сценарий для объёмного материала: сначала создай статью с одним name (или с name и первыми несколькими блоками), затем добавляй остальной текст порциями через modify_article_blocks (операция insert, до 50 блоков за вызов). Если получил ошибку «name: Field required», не повторяй тот же вызов — раздели текст на части.

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": {
      "name": "<name>"
    },
    "name": "create_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoМассив блоков статьи. Поддерживаемые типы блоков: paragraph — {text} (HTML-инлайн: <b>, <i>, <a href>, <mark>, <code>); header — {text, level} (level: 1-6); list — {style, items} (style: ordered/unordered, items: вложенные {content, items}); image — {file: {url}, caption, withBorder, stretched, withBackground}; quote — {text, caption, alignment}; code — {code}; delimiter — {}; table — {withHeadings, content} (content: 2D массив строк).Простой пример: [{"type":"header","data":{"text":"Заголовок", "level":1}}, {"type":"paragraph","data":{"text":"Текст"}}]
nameYesНазвание статьи (1-255 символов)

Output Schema

NameRequiredDescriptionDefault
idYesИдентификатор статьи
bodyNoМассив блоков содержимого статьи
nameYesНазвание статьи
extraDataNoДополнительные данные статьи
hasInvitesNoЕсть ли у статьи приглашения к совместному редактированию
dateCreatedNoДата создания статьи в формате ISO 8601
dateUpdatedNoДата последнего обновления статьи в формате ISO 8601

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does well: it discloses a real failure mode (large body truncated by model output limits, producing a request missing the required name), the validation error text to expect, and the recovery path. It leaves out permissions/ownership and what happens on duplicate names, which keeps it from 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?

Purpose is front-loaded in one short sentence, then the risky case is flagged in capitals, then the reliable scenario. Slightly verbose in repeating the truncation cause and the error-recovery advice, but every sentence carries operational value.

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?

An output schema exists, so return values needn't be described, and the description covers the one genuinely dangerous aspect of this tool: oversized payloads. Auth scoping and post-create visibility are unaddressed, but nothing needed to call it correctly 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, and the description earns an extra point by explaining body sizing constraints and safe chunking strategy rather than restating block shapes. It does not add syntax detail for name beyond the schema's own 1-255 constraint.

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

Purpose4/5

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

The opening sentence gives a specific verb and resource ('Создать новую статью') and the body immediately explains two creation modes. It does not explicitly differentiate from close siblings like set_article_content or replace_article_text, so an agent must still infer which creation/editing tool to pick beyond the one sibling it names.

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?

It gives explicit branching: short articles go in the body in one call; long articles should start with name only (or name plus a few blocks) and be extended via modify_article_blocks insert up to 50 blocks per call. It also names the failure case ('name: Field required') and forbids retrying the identical call, which is actionable when-to/when-not guidance.

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