NotebookLM MCP

Delete source

source_delete

DestructiveIdempotent

Permanently removes a source from a notebook after explicit approval; set confirm=true to delete, or confirm=false to preview a pending confirmation.

Instructions

Permanently remove one source from a notebook. With confirm=false it does nothing and returns pending_confirmation; with confirm=true it deletes and returns a confirmation message. This cannot be undone: name the source to the user and get explicit approval first.

Input Schema

Name	Required	Description
`confirm`	Yes	Must be true to delete. With false the tool only returns pending_confirmation
`source_id`	Yes	Source ID, as listed in the notebook's sources by notebook_get
`notebook_id`	Yes	Notebook ID, as returned by notebook_list or notebook_create

Output Schema

Name	Required	Description	Default
`status`	Yes
`message`	No	Human-readable outcome or next step

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.5.0Oct 20, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "message": {
+      "description": "Human-readable outcome or next step",
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "success",
+        "pending_confirmation"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}

Changed3 schema fields changedv0.4.0Oct 20, 2026

changedInput schema / properties / confirm / description

Previous value: -"Must be true to confirm deletion"New value: +"Must be true to delete. With false the tool only returns pending_confirmation"

changedInput schema / properties / notebook_id / description

Previous value: -"The notebook ID"New value: +"Notebook ID, as returned by notebook_list or notebook_create"

changedInput schema / properties / source_id / description

Previous value: -"The source ID"New value: +"Source ID, as listed in the notebook's sources by notebook_get"

First observedv0.3.1Aug 6, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds materially beyond them: the dry-run behavior of confirm=false, the returned sentinel value pending_confirmation, the irreversibility warning, and the human-approval requirement. This is exactly the extra behavioral context a destructive tool should carry.

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?

Three sentences, zero filler: the destructive purpose leads, the confirm semantics follow, and the safety warning closes. Each sentence earns its place and the most important constraint (irreversible) is not buried.

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 three-parameter destructive tool with an output schema and full annotation coverage, the description supplies everything an agent needs: what happens on each confirm value, the return sentinel, the irreversibility, and the approval gate. Nothing required for correct invocation is missing.

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 description coverage is 100%, so the schema already documents notebook_id, source_id, and confirm. The description restates confirm's semantics ('with confirm=false it does nothing') but adds no syntax, format, or sourcing detail beyond what the schema provides; baseline 3 applies.

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 remove one source from a notebook') and scopes it to a single source within a notebook, clearly distinguishing it from read siblings like source_get and source_get_content. An agent can tell immediately what this does without opening the schema.

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?

Explains the two-step confirmation flow (confirm=false returns pending_confirmation, confirm=true deletes) and adds a procedural rule: name the source to the user and get explicit approval first. There is no competing delete sibling to disambiguate against, so the absence of named alternatives is acceptable, but no explicit 'do not use for X' boundary is given.

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