Skip to main content
Glama

Polyblog Multilingual Blog

by io.polyblog
OverviewDiscussionsAdmin

Create a new blog

create_blog
Destructive

Use this when someone asks to start a new blog in Polyblog with a given name and languages. Returns the new blog's id, name, domain and languages; the name becomes the public .polyblog.io subdomain, so a name already taken fails. Not for adding a post to an existing blog.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesBlog name, which becomes the public <name>.polyblog.io subdomain and has to be globally unique
localesNoEvery language the blog publishes in, ISO 639-1 codes such as en and it
descriptionNoShort description of what the blog is about, up to 600 characters
defaultLocaleNoMain language, an ISO 639-1 code such as en
articlesFormatNoFormat for the blog's posts: markdown or html

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
blogYes
statusYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedOutput schema / properties / blog / properties / coverUrl / $ref
      Added value: +"#/properties/blog/properties/logoUrl"
    • removedOutput schema / properties / blog / properties / coverUrl / anyOf
      Removed value: -[
-  {
-    "maxLength": 2048,
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • addedOutput schema / properties / blog / properties / logoUrl
      Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 2048,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
    • changedOutput schema / properties / blog / required
      Previous value: -[
-  "id",
-  "name",
-  "customDomain",
-  "defaultLocale",
-  "locales",
-  "localesTruncated",
-  "coverUrl",
-  "created",
-  "edited"
-]New value: +[
+  "id",
+  "name",
+  "customDomain",
+  "logoUrl",
+  "defaultLocale",
+  "locales",
+  "localesTruncated",
+  "coverUrl",
+  "created",
+  "edited"
+]
  2. Changed5 schema fields changed
    • addedInput schema / properties / articlesFormat / description
      Added value: +"Format for the blog's posts: markdown or html"
    • changedInput schema / properties / defaultLocale / description
      Previous value: -"ISO 639-1 code the blog writes in by default, e.g. \"en\""New value: +"Main language, an ISO 639-1 code such as en"
    • addedInput schema / properties / description / description
      Added value: +"Short description of what the blog is about, up to 600 characters"
    • changedInput schema / properties / locales / description
      Previous value: -"ISO 639-1 codes the blog publishes translations in"New value: +"Every language the blog publishes in, ISO 639-1 codes such as en and it"
    • changedInput schema / properties / name / description
      Previous value: -"Blog name; also becomes the public <name>.polyblog.io subdomain and must be globally unique"New value: +"Blog name, which becomes the public <name>.polyblog.io subdomain and has to be globally unique"
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations cover the safety profile (destructiveHint=true, idempotentHint=false, openWorldHint=true), and the description adds genuinely useful behavior: the name must be globally unique because it becomes the public <name>.polyblog.io subdomain, and duplicate names fail. That failure-mode disclosure goes beyond what the annotations provide.

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

Conciseness5/5

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

Three tight sentences: trigger first, then return/failure semantics, then exclusion. Every clause earns its place and nothing is padded.

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?

An output schema exists, yet the description still concisely signals return fields and, more importantly, the collision failure mode. Combined with annotations covering safety, an agent has everything needed to invoke correctly.

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 description coverage is 100%, so all five parameters (including the required 'name' and its uniqueness/length constraint) are already documented. The description reinforces the name-to-subdomain mapping but adds no syntax or format detail beyond the schema, matching the baseline for full coverage.

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?

Specific verb+resource (create a blog) with scope, and it explicitly distinguishes itself from the sibling operation by function: 'Not for adding a post to an existing blog.' An agent can route correctly without opening the schema.

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?

'Use this when someone asks to start a new blog in Polyblog' gives a clear trigger, and the closing exclusion rules out the most likely confusion (adding a post). It stops short of naming the concrete alternative (create_article), so it is strong but not fully explicit routing.

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

All Polyblog Multilingual Blog 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