MCP server for generating and creating social media posts using AI, with integration to X (Twitter)
This server has 2 tools with critical definition quality gaps. Both tools have names that do not follow verb_noun conventions and lack parameter descriptions. The 'addTwoNumbers' tool is a trivial utility with no real-world use case. The 'createPost' tool is a write operation that exposes a plain status parameter without any constraint documentation. Parameter descriptions are entirely null/missing for both tools, violating the baseline requirement that 100% of A+ tool params have descriptions. Descriptions exist but are minimal (8-54 chars, below the 34-char p10 baseline for acceptable tools). No error handling guidance is provided, agents calling createPost will have no recovery path if the API fails or the status is invalid. Output schemas are not documented. Neither tool supports composition, there's no way for the agent to validate input before calling createPost, and no feedback on what the post creation actually returned.
Add two numbers
Create a post on X formally known as Twitter
Tool naming does not follow verb_noun convention. 'addTwoNumbers' should be 'add_numbers' (camelCase used instead of snake_case, and includes indirect object). 'createPost' is acceptable but lacks clarity on which service (X/Twitter).
All input parameter descriptions are null/missing. LLMs cannot determine what 'a', 'b', and 'status' mean without descriptions. Baseline requires 100% of A+ tool params have descriptions; this server has 0%. Violates critical check: 'Every parameter needs a description explaining what it controls.'
No output schema documentation. Agents do not know what createPost returns, is it a post ID? Full post object? Status code? Missing output schemas prevent downstream tool chaining and force agents to guess what fields are available.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 38 | 2026-07-28+ | v2 |
| 2026-03-09 | F | 31 | - | v1 |
createPost is a destructive write operation but has no error handling guidance, confirmation pattern, or recovery steps. If the X API fails, the agent has no guidance on whether to retry, ask the user, or escalate. Pattern violation: 'Error responses must tell the LLM what to do next.'
No input validation or constraints documented. The 'status' parameter for createPost accepts any string, no length limits, character restrictions, or format guidance. X/Twitter has tweet length limits (280 chars); this should be enforced or documented. Agents will frequently pass oversized strings.
Tool descriptions are too short (8-54 chars, well below 34-char p10 baseline). 'Add two numbers' and 'Create a post on X formally known as Twitter' lack context on WHEN to use them, WHAT they return, or HOW they interact with other tools. Minimal descriptions force LLMs to guess intent.
No permission checks or scope declarations. createPost can write to X without any authorization validation. No audit trail, no scope hints (e.g., 'write:tweets'). Pattern violation: 'Each tool should declare what permissions it requires.'
addTwoNumbers is a trivial utility with no real-world use case. It does not align with the server's stated purpose (Intellipost.ai, an AI post generator). Including tools that don't serve the agent's goals dilutes focus and wastes the LLM's decision bandwidth.