Vendooly

wp_create_post

ACTION on the WordPress site. Creates a blog post. content is HTML (WordPress blocks optional). Default status is draft (not visible to readers); use publish only if the user explicitly asks, or future with date (ISO 8601) to schedule. In safe mode the first call returns a PREVIEW with confirm_id: show it and call again with confirm_id only after the user approves. Not retried on network errors (no duplicates): if it times out, check with wp_list_posts before retrying.

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": {
      "site_id": "<site_id>",
      "title": "<title>",
      "content": "<content>"
    },
    "name": "wp_create_post"
  }
}

Input Schema

Name	Required	Description
`date`	No	ISO 8601 publish date (required for future)
`slug`	No	Slug URL dell'articolo, minuscolo con trattini, es. come-scegliere-il-prezzo.
`tags`	No	Tag ids from wp_list_terms
`title`	Yes	Titolo dell'articolo.
`status`	No	Default draft
`content`	Yes	Post body, HTML
`excerpt`	No	Estratto dell'articolo, testo semplice.
`site_id`	Yes	Id sito WordPress (da wp_list_sites).
`categories`	No	Category ids from wp_list_terms
`confirm_id`	No	Token di conferma ritornato dall'anteprima. Ripassa lo STESSO payload + confirm_id per eseguire davvero la scrittura.
`featured_media`	No	Media id already in the WordPress library

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 9, 2026

addedInput schema / properties / excerpt / description

Added value: +"Estratto dell'articolo, testo semplice."

addedInput schema / properties / site_id / description

Added value: +"Id sito WordPress (da wp_list_sites)."

addedInput schema / properties / slug / description

Added value: +"Slug URL dell'articolo, minuscolo con trattini, es. come-scegliere-il-prezzo."

addedInput schema / properties / title / description
```
Added value: +"Titolo dell'articolo."
```

AddedNov 3, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses that the default state is a non-public draft, that safe mode returns a PREVIEW with confirm_id requiring a second call after user approval, and that the operation is not retried on network errors to avoid duplicates. These are non-obvious behavioral facts that materially change how an agent should sequence the call.

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?

The most important constraints, defaults and the confirm-flow, are front-loaded in a compact paragraph with no filler sentences. The leading fragment "ACTION on the WordPress site" is slightly redundant with the tool's own naming and annotations, but every subsequent clause carries real instruction.

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 an 11-parameter, no-output-schema mutation tool, the definition covers defaults, scheduling, the two-step confirm flow, and error handling. It never hints at what a successful creation returns (e.g., post id) or what the preview payload looks like beyond confirm_id, which is the main remaining gap given there is no output schema.

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 coverage is 100%, so the schema already documents all 11 parameters including status enum, ISO 8601 date, and confirm_id. The description adds some meaning (content is HTML, blocks optional; draft-by-default) but largely restates what the schema says, so the baseline of 3 applies.

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 opens with a clear verb+resource pair ("Creates a blog post") and marks it as a mutating action on the WordPress site, so an agent can immediately tell it apart from the list-oriented siblings such as wp_list_posts or wp_list_sites. It does not explicitly contrast itself with wp_update_post, which is the nearest confusion risk, so it stops short of full sibling differentiation.

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 states concrete when-to-use rules for the risky parameters: default draft, publish only on explicit user request, future with an ISO 8601 date for scheduling. It also names the recovery path when the call times out (check with wp_list_posts before retrying), which is exactly the routing guidance an agent needs.

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

All Vendooly tools Inspect

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

Need Help?