create_siteAdd a new site to the account. Language/market is auto-detected from the homepage. Requires an available paid site slot (use create_checkout first if none). Returns the new siteId. (requires an agent API key)
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| niche | No | ||
| domain | Yes | Bare domain, e.g. example.com | |
| brandVoice | No | ||
| description | No | ||
| publishWebhookUrl | No | ||
| publishIntegration | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / publishIntegration / enumPrevious value: -[
- "none",
- "webhook",
- "wordpress",
- "ghost",
- "shopify",
- "rest",
- "nextjs"
-]New value: +[
+ "none",
+ "webhook",
+ "wordpress",
+ "ghost",
+ "shopify",
+ "webflow",
+ "rest",
+ "nextjs"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint/destructiveHint annotations, the description discloses important behaviors: it creates a site, auto-detects language/market from the homepage, consumes/requires a paid slot, and returns the new siteId. It also mentions the auth requirement. These are non-obvious side effects and prerequisites that annotations do not convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences, each carrying essential information: the action, a behavioral detail, a precondition, and the return value. No filler or repetition of schema properties. The structure is front-loaded with the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a creation tool with no output schema, the description covers the key context an agent needs: what gets created, the paid-slot prerequisite, authentication, and the siteId return. The only notable gap is that 6 of 7 parameters remain semantically unexplained, but since only 2 are required, an agent can still invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 14%, with only 'domain' having an inline description. The description adds no meaning for 'name', 'niche', 'brandVoice', 'description', 'publishWebhookUrl', or 'publishIntegration'. Since the schema leaves most parameters undocumented, the description needed to compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Add a new site to the account.' It distinguishes itself from siblings by stating it creates a site, returns a siteId, and has a payment prerequisite referencing create_checkout. This is enough for an agent to know exactly what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly includes the prerequisite: 'Requires an available paid site slot (use create_checkout first if none).' This gives concrete conditional guidance and names the relevant sibling tool. It also notes the agent API key requirement, helping the agent know when it can call this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, but word-counter and character-counter overlap heavily, and meta-tag-generator subsumes several other generators (title, description, canonical). The sheer number of adjacent content generators creates some ambiguity, though descriptions generally clarify.
Tool names are inconsistent: some use snake_case (create_site, get_article, list_articles) while others use hyphenated lowercase (ad-copy-generator, meta-tag-generator, robots-txt-generator). This mixing of conventions makes it hard for an agent to predict the name for a given action.
With 59 tools, the server is heavily over-scoped for a typical MCP server. Many tools are similar (various calculators, many content generators) and could be consolidated, making the surface bloated and harder to navigate.
The server covers a broad range of SEO tasks: site management, article generation/publishing, analytics, technical SEO, and content tools. However, there are gaps such as missing update/delete operations for articles and no backlink analysis, leaving some workflows incomplete.