Skip to main content
Glama

Outil.io

Create article page

create_article_page

PAGE ARTICLE À MODIFIER : chaque article actif a déjà sa page publiée automatiquement avec le modèle par défaut. Cet outil crée (ou renvoie) la page modèle modifiable d’un blog — en-tête et pied de page de l’accueil, titre, date, auteur, résumé, image et corps de l’article (composant article-body) aux polices et couleurs du site — et la publie. Chaque article actif du blog est alors publié à /p//<slug de l’article> (et / sur le domaine du site), et les listes dynamiques y renvoient. Se modifie comme une page (get_page_structure / apply_page_changes) : les blocs reliés (custom.binding title/excerpt/image/date/category/author) et le corps sont remplis pour chaque article ; le corps, le titre et le résumé s’allongent avec le texte. blogId absent = modèle de tous les blogs. convert_group target collection la crée déjà.

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": "create_article_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
blogIdNo
sourcePageIdNopage qui montre la liste (bouton de retour) ; sinon l’accueil

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and the description adds meaningful context beyond them: it publishes live pages at /p/<project>/<slug>, that all active articles become published and dynamic lists point there, that bound blocks are auto-filled per article, and notably that it may return an existing page rather than create a new one. That 'creates (or returns)' behavior is exactly the kind of non-obvious trait annotations cannot express. It leaves out permission requirements and what happens on repeated calls, so 4 rather than 5.

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

Conciseness3/5

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

The content is largely relevant, but it is delivered as one dense run-on paragraph with parenthetical asides (components, binding keys, slug patterns) that make it hard to scan. It is front-loaded with an all-caps French label ('PAGE ARTICLE À MODIFIER') that is more UI jargon than agent-facing signal. Trimming and splitting into purpose / behavior / alternatives would help considerably.

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 a two-parameter creation tool with no output schema, the description covers scope (all blogs when blogId is absent), side effects (publication of every active article, dynamic list links), and how to further modify the result. Missing pieces are secondary: return value shape, error/duplicate behavior, and required permissions. Overall an agent could call this correctly from the description.

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 50%: sourcePageId is documented in the schema, blogId is not. The description compensates on the undocumented one by explaining that an absent blogId yields a template for all blogs, which is genuine semantic value not in the schema. It does not elaborate on sourcePageId, but the schema already covers that, so the combined picture is adequate.

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 description states a specific verb and resource: it creates (or returns) the editable template page for a blog's articles, naming the concrete contents (header/footer from home, title, date, author, excerpt, image, article-body component) and the resulting publish path. It is clearly more than a restatement of the name, and it clarifies a non-obvious point — this is the article *template*, not a per-article page. It stops short of differentiating itself from the sibling create_blog_page/create_page tools, so it is not a 5.

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

Usage Guidelines3/5

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

Usage is conveyed indirectly: the opening line notes that every active article already has an auto-published page with the default template, implying this tool is only needed to obtain a customizable version, and the closing line warns that convert_group with a target collection already creates it. Editing is routed to get_page_structure / apply_page_changes. However, there is no explicit 'use this when / do not use this when' statement, and the relationship to create_blog_page and create_page 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.