WebinarStack

Delete Interaction

webinarstack.webinars.interactions_delete

Destructive

Permanently delete a poll or CTA interaction from a tenant-owned webinar. This action is irreversible and high-risk on a live webinar where polls and CTAs display to real attendees. WARNING: Deleting a poll permanently removes all its recorded poll_vote_snapshots (per-attendee votes) via ON DELETE CASCADE — this data is NOT recoverable from the returned snapshot (the snapshot recreates the poll config only, not the vote data). Deleting a CTA offer clears the attribution_offer_id pointer on any purchase_records via ON DELETE SET NULL — the revenue and refund ledger rows survive, only the attribution link is lost. Before deleting, consider whether the interaction has live engagement. The response returns a full snapshot of the deleted interaction for config-only recovery.

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": {
      "webinarId": "<webinarId>",
      "interactionId": "<interactionId>"
    },
    "name": "webinarstack.webinars.interactions_delete"
  }
}

Input Schema

Name	Required	Description	Default
`webinarId`	Yes
`interactionId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes far beyond destructiveHint=true by disclosing the exact cascade behavior (poll_vote_snapshots removed, votes unrecoverable), the SET NULL effect on purchase_records attribution with ledger rows surviving, and what the returned snapshot can and cannot restore.

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-loads the irreversible action and the two data-loss consequences, with every sentence carrying concrete information; the 'consider whether the interaction has live engagement' sentence is the weakest and mildly restates the earlier warning.

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

Completeness5/5

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

With no output schema, the description helpfully explains what the response returns and its limits; combined with the data-loss disclosures, an agent has everything needed to decide whether and how to call this destructive tool.

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 0%, so the description carries the burden; it clarifies that interactionId refers to either a poll or a CTA and that webinarId must be a tenant-owned webinar, but adds no format, validity, or lookup guidance for the two UUIDs.

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 ('Permanently delete a poll or CTA interaction') and scopes it to tenant-owned webinars, which clearly separates it from siblings such as interactions_update, interactions_get, and interactions_list.

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 a clear precondition ('Before deleting, consider whether the interaction has live engagement') and implies recovery via the returned snapshot, but never names an explicit alternative (e.g. update instead of delete) or states when deletion is the wrong choice.

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

All WebinarStack 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?