AI Separations

Buy a credit pack (hosted checkout)

buy_credits

Start a purchase of an AI Separations credit pack for the user and return a Stripe Checkout link. Packs: credits_sample ($29, 10 separations), credits_shop ($99, 50). Credits never expire; 1 credit = 1 full separation via separate_image. Requires the user's email: the API key is emailed there after payment. Nothing is charged by this tool — the user pays on the returned link.

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": {
      "email": "<email>"
    },
    "name": "buy_credits"
  }
}

Input Schema

Name	Required	Description	Default
`pack`	No	Which credit pack (default credits_sample)
`email`	Yes	The buyer's email — receipt and API key go here

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 23, 2026

changedInput schema / properties / pack / enum

Previous value: -[
-  "credits_sample",
-  "credits_shop",
-  "credits_studio"
-]New value: +[
+  "credits_sample",
+  "credits_shop"
+]

First observedOct 9, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing that the tool only creates a hosted Stripe Checkout session and does not charge, that payment happens off-tool on the returned link, that credits never expire, and that the API key arrives by email after payment. These are exactly the semantics an agent needs before triggering an external, non-idempotent flow.

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?

Four short sentences, front-loaded with the action and return value, then pack details, then the email prerequisite, then the no-charge clarification. Every sentence carries information not available elsewhere.

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?

With no output schema, the description correctly explains what is returned (a Stripe Checkout link) and covers credit consumption semantics. The one gap is that it doesn't warn that repeated calls create separate checkout sessions (non-idempotent), which matters for a purchase flow.

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 100% so the baseline is 3; the description adds real value by expanding the enum meaning — pack prices ($29/$99) and what each buys (10 vs 50 separations) — which the schema only names. It also reinforces why email is required (key delivery).

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?

States a specific verb and resource ('Start a purchase of an AI Separations credit pack') and names the concrete artifact returned ('Stripe Checkout link'). This is unmistakably distinct from siblings check_credits and get_pricing, which inspect rather than initiate purchases.

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?

Gives clear context (purchase initiation) and a prerequisite (the user's email, because the API key is emailed there), plus the key caveat that nothing is charged here. It doesn't explicitly route to alternatives (e.g., 'use check_credits to see remaining balance first' or 'get_pricing for current prices'), so an exclusion statement is the only missing piece.

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

All AI Separations 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?