Permanently removes a tag from Paperless-NGX and strips it from all linked documents. Requires confirmation to prevent accidental deletion.
⚠️ DESTRUCTIVE: Permanently delete a tag from the entire system. This will remove the tag from ALL documents that use it. Use with extreme caution.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| confirm | Yes | Must be true to confirm this destructive operation |
Changes observed during successful MCP inspections.
v2.2.1Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / confirmAdded value: +{
+ "description": "Must be true to confirm this destructive operation",
+ "type": "boolean"
+}Input schema / requiredPrevious value: -[
- "id"
-]New value: +[
+ "id",
+ "confirm"
+]v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden, and it does disclose the key traits: the operation is destructive, permanent, and cascades across the entire system. It omits auth/permission requirements, whether the deletion is recoverable, and what happens to the tag's other relationships, but the core behavioral risk is clearly surfaced.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with the destructive warning front-loaded. The trailing caution sentence is somewhat redundant with the opener but small enough not to be wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter delete with no output schema, the description is largely complete: it conveys destructiveness, permanence, and global scope. Missing only the param explanation for id and any auth/cascade-recovery context, which are minor for this tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 50%: the confirm parameter is self-documented, but id has no description in the schema and none in the description either. The description adds no parameter-level meaning beyond the schema, so it neither compensates for the gap nor confuses anything.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (delete) and resource (tag), and goes further by scoping the effect: 'from the entire system' and 'from ALL documents that use it.' An agent can distinguish this from sibling tag tools like update_tag or bulk_edit_tags immediately.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Use with extreme caution' is a warning, not usage guidance. It never says when to prefer this over alternatives such as update_tag (removing a tag from a single document) or bulk_edit_tags, nor does it state preconditions beyond the schema's confirm flag.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.