Skip to main content
Glama
thenavidm

substack-mcp

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Delete a draft

delete_draft
Destructive

Permanently remove an unpublished Substack draft only after explicit confirmation; no undo or trash recovery, so confirmation is required.

Instructions

Permanently delete an unpublished draft. There is no undo and no trash to recover it from, so this refuses to run without confirm: true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesDraft id to delete.
confirmNoSet true only when the user asked for exactly this action.
publicationNoWhich connected publication to act on, matched loosely against its hostname (for example 'example.substack.com' or just 'example'). Defaults to the first connected publication.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv3.0.1
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • removedInput schema / additionalProperties
      Removed value: -false
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true for this to run. This action cannot be undone, so it is refused without an explicit confirmation."New value: +"Set true only when the user asked for exactly this action."
  2. First observedv2.1.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds substantive context beyond them: irreversibility ('no undo and no trash to recover it from') and a hard guard requiring confirm: true. That is real behavioral disclosure rather than a restatement of the hints.

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?

Two tight sentences, front-loading the destructive nature first and the guard condition second. Every clause carries information; nothing is padded.

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 destructive mutation with no output schema, the description covers irreversibility, the confirmation requirement, and the target resource. It omits mention of the publication-scoping parameter's default behavior, though the schema documents that, leaving only a minor gap.

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, but the description adds consequence-level meaning for 'confirm' by framing it as a mandatory gate tied to user intent, which the schema alone only partially conveys. It does not add anything for 'id' or 'publication', which the schema already documents well.

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+resource ('Permanently delete an unpublished draft') and scopes it to drafts, which distinguishes it from the sibling delete_note and from update_draft/get_draft. An agent can identify the operation immediately.

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 for invocation ('refuses to run without confirm: true') and, via the confirm parameter semantics, ties use to the user explicitly requesting the action. It does not name sibling alternatives (e.g., delete_note), so it falls short of the 5-level routing guidance.

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

Deploy Server

Other Tools