Skip to main content
Glama
retensy
by retensy

article_publish

Publishes a new Retensy blog article from Markdown content. Automatically extracts the title, cover image, and SEO excerpt, then returns the article ID, slug, and public URL.

Instructions

Опубликовать НОВУЮ статью блога retensy (POST /api/articles). content — Markdown (как README на GitHub: заголовки, списки, таблицы, код, картинки по URL). title необязателен: если не передать, заголовком станет первая строка вида «# Заголовок», и она убирается из текста. Обложку можно задать явно через cover (URL картинки) — иначе берётся первая картинка из текста; excerpt (SEO-описание) тоже можно задать явно, иначе генерируется из текста. Возвращает статью с id и slug + публичный URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
coverNoURL обложки (coverImage/OG). Если не задан — берётся первая картинка из текста.
titleNoЗаголовок (необязателен, если content начинается с «# ...»)
contentYesТело статьи в Markdown
excerptNoКраткое SEO-описание (≤160 симв). Если не задан — генерируется из текста.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does so creditably: it documents the fallback chain for title (first "# ..." line, which is then stripped from the body), cover (first image), and excerpt (auto-generated), and names the return payload (id, slug, public URL). It omits auth requirements, error behavior, and any note that publishing is an irreversible public write.

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 and endpoint are front-loaded, and each subsequent sentence covers a distinct parameter's default behavior. It is on the dense side but nothing is redundant given the absence of annotations.

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?

With no output schema, the description correctly supplies the return shape (article with id, slug, public URL), and it explains all four parameters' fallback logic. The remaining gap is operational context such as auth and failure modes, minor for a straightforward publish call.

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 baseline is 3, but the description adds genuine meaning beyond the schema: it explains the conditional interplay between title and the content's leading heading and notes that the heading is removed from the body text, a behavior the schema does not state.

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?

The description gives a specific verb+resource ("Опубликовать НОВУЮ статью блога retensy") and pins the exact endpoint (POST /api/articles). The emphasized "НОВУЮ" plus the POST signature clearly separates it from the sibling article_update/article_get/article_list tools.

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 states the creation context and stresses that the article must be NEW, which implicitly routes edits to article_update. However, it never names article_update explicitly or describes when publishing would be inappropriate, so the alternative 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.