Sonar Connections

Delete one of your unpublished drafts (hosts)

event_draft_delete

DestructiveIdempotent

Deletes one of the signed-in person's own unpublished drafts for good, with its guest details and uploads, as the organizer dashboard's Delete draft does. eventIdOrName is the draft's id or its name as the host says it. FIRST CALL WITHOUT confirm returns a PREVIEW naming the draft with a requestId and deletes nothing; read it out, and only when the host says yes, call again with confirm: true and that requestId. A published event cannot be deleted (NOT_A_DRAFT). Only the host can delete. The reply names what was deleted and the new count of open drafts. Refusals (NOT_FOUND, NOT_AUTHORIZED, NOT_A_DRAFT, CONFIRM_INVALID, DELETE_FAILED) are read out as given. It requires a personal connector token.

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": {
      "eventIdOrName": "<eventIdOrName>"
    },
    "name": "event_draft_delete"
  }
}

Input Schema

Name	Required	Description
`confirm`	No	Absent on the first call, which deletes nothing; true with requestId deletes.
`requestId`	No	The requestId the first call returned.
`eventIdOrName`	Yes	The draft's event id or its name as the host says it.

Output Schema

Name	Required	Description	Default
`ok`	No
`code`	No
`name`	No
`error`	No
`deleted`	No
`message`	No
`preview`	No
`servedBy`	No
`requestId`	No
`openDrafts`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.6/5.0

Behavior5/5

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

It goes well beyond the destructive annotation. It discloses that deletion is permanent, that guest details and uploads go with the draft, and that the preview step deletes nothing. It also covers the personal connector token requirement, the reply contents (what was deleted plus the new open-draft count), and the enumerated refusal codes. None of this contradicts the annotations.

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 description is dense and front-loaded, and capitalization emphasizes the critical preview step. It runs somewhat long, and the dashboard comparison adds little, but most sentences earn their place.

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?

For a destructive, two-phase tool with an output schema, it covers purpose, the confirmation protocol, auth, constraints, error codes, and the reply summary. Nothing essential is missing.

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%, yet the description adds real meaning. It explains how confirm and requestId interact across the two calls and that eventIdOrName accepts a natural-language name as the host says it.

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?

It names a specific verb and resource: permanently deletes the signed-in person's own unpublished drafts, including guest details and uploads. It separates drafts from published events (NOT_A_DRAFT), which marks the scope against siblings like event_publish and event_draft_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?

It sets out the two-step workflow: preview without confirm, read it out, then call with confirm:true and the requestId once the host agrees. It also states the exclusions (published events, non-hosts). It does not name an alternative for published events, such as a cancel or unpublish path, or point to event_draft_list for finding drafts.

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

All Sonar Connections 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?