Tulina

stripe_payment

Read-only

Payments — read-only. Refunding is not available in this connector.

For "why did this payment fail": the PaymentIntent's last_payment_error is authoritative (code, decline_code, message); on a Charge, prefer outcome.seller_message, which is written for the merchant.

Disputes carry a hard deadline in evidence_details.due_by, and the money is already withdrawn from the balance while one is open — surface them proactively rather than on request.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "stripe_payment"
  }
}

Input Schema

Name	Required	Description	Default
`op`	No	"list_charges" (default) \| "get_charge" \| "list_intents" \| "get_intent" \| "list_refunds" \| "get_refund" \| "list_disputes" \| "get_dispute".	list_charges
`_org`	No	Org (id) de CET APPEL. `oto_list_orgs()`.
`limit`	No
`_group`	No	Équipe (id) de CET APPEL, sous son org parente.
`_run_id`	No	OBLIGATOIRE à chaque appel dès `run_start` ou `data_claim_next` : sans lui, l'écriture sur une ligne réservée est refusée. Hérité seulement si le serveur tient un run actif — n'y compte pas.
`_project`	No	Projet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
`_instance`	No	Instance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
`charge_id`	No
`refund_id`	No
`dispute_id`	No
`customer_id`	No
`created_after`	No
`created_before`	No
`starting_after`	No
`payment_intent_id`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

B3.4/5.0

Behavior4/5

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

Consistent with readOnlyHint=true, and it adds context the annotation cannot: refunds are unavailable in this connector, dispute money is already withdrawn from the balance, and evidence_details.due_by is a hard deadline. These are real operational facts that affect how an agent should behave; only the absence of pagination/result-size behavior keeps it from a 5.

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 read-only constraint and the refund limitation are front-loaded, and each subsequent paragraph addresses one problem (failure diagnosis, disputes). The parenthetical field lists are slightly dense but every sentence carries actionable content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema existence means return values needn't be explained, and the description wisely spends its words on error interpretation and dispute urgency. But for an 8-operation, 15-parameter tool it omits how to select an operation and how to scope/paginate queries, which are the main things an agent must get right before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 40% across 15 parameters, and the description adds no meaning for any of them — no explanation of the op enum choices, no filter semantics for customer_id/created_after/created_before, and no guidance on starting_after pagination. The free-text paragraphs instead describe response fields (last_payment_error, outcome.seller_message), leaving the unlabeled input parameters undocumented in both places.

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 opening line 'Payments — read-only' establishes the resource and a key constraint, and the body makes clear it covers PaymentIntents, Charges and Disputes. It never enumerates that this is a multiplexed read tool spanning list/get for intents, charges, refunds and disputes, so an agent must open the schema to learn the actual surface.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete guidance for two scenarios — diagnosing a failed payment and surfacing disputes proactively — which is genuinely useful. It says nothing about when to pick this tool over stripe_search, stripe_invoice or stripe_balance, and no exclusions beyond 'refunding is not available', so sibling routing is left to inference.

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

All Tulina 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?