Tulina

stripe_event

Read-only

The account's activity feed — every state change, newest first, with the affected object embedded in data.object.

⚠️ Stripe keeps events for 30 DAYS only. Any question about a longer period ("this quarter", "last year") will silently come back short here — use stripe_invoice(op="totals") or the list ops, which read the objects themselves and have no such window.

"webhook_endpoints" lists which integrations are listening, for diagnosis. Creating or deleting them is not available here: deleting one silently breaks whatever automation depended on it.

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_event"
  }
}

Input Schema

Name	Required	Description	Default
`op`	No	"list" (default) \| "get" \| "webhook_endpoints".	list
`_org`	No	Org (id) de CET APPEL. `oto_list_orgs()`.
`type`	No	"list" filter, wildcards allowed — `invoice.*`, `invoice.payment_failed`, `customer.subscription.deleted`.
`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')`.
`event_id`	No	REQUIRED by "get" (`evt_…`).
`_instance`	No	Instance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
`created_after`	No
`created_before`	No
`starting_after`	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

A4.3/5.0

Behavior4/5

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

With readOnlyHint already declaring the safety profile, the description earns credit for disclosing a real behavioral trait an agent cannot infer: the 30-day event retention with *silent* truncation, plus the newest-first ordering and the 30-day caveat's consequence. The warning that deleting a webhook endpoint silently breaks dependent automation is useful sibling context. It stops short of describing pagination behavior beyond the starting_after param or the response shape for the get op, so it is not exhaustive.

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?

Front-loaded: the one-line definition comes first, then the highest-stakes caveat (30-day window) in bold, then the op-specific note. Three short paragraphs, no filler. Minor deductions for the awkwardly quoted and loosely attached final paragraph about webhook_endpoints, which reads like a fragment.

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 a 12-parameter, read-only tool with an output schema, the description covers the two things an agent must know before calling: the retention window that causes misleading empty results, and what the alternate ops do. The undocumented limit/created_after/starting_after params and the get-op flow remain gaps, but the output schema and enum carry some of that load.

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 67%: op, type, event_id and the internal _org/_project/_instance/_run_id params are documented, but limit, created_after, created_before and starting_after are bare in both places. The description never mentions the type wildcard filter or time-window params, so it adds no meaning beyond the schema. Baseline 3 is appropriate given moderate coverage.

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?

Opens with a concrete definition of the resource ('The account's activity feed — every state change, newest first') and even states the shape of the payload ('the affected object embedded in data.object'). It distinguishes the tool's scope from the list ops and stripe_invoice, so an agent can tell which tool to reach for without opening a schema.

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?

Gives an explicit when-NOT-to-use rule with a reason (the 30-day retention window makes longer periods come back silently short) and names the alternatives to use instead: stripe_invoice(op="totals") and the list ops. It also frames the webhook_endpoints op as a diagnostic path and states that creating/deleting endpoints is unavailable here.

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?