Achriom

Remove from my library

remove

DestructiveIdempotent

Remove something. what: library (a title from their library: needs media_type and item_id, from query), list_entry (a title from a list), list (a whole list; its titles stay), event (one history entry: event_id or event_date, or all), pin (off their page), episode (mark episodes unwatched), challenge (a whole challenge: name; its titles stay), challenge_pick (the title off a challenge prompt: challenge, prompt or slot_id), shelf (a whole shelf with its entries: name, and confirm: true once they said yes), shelf_entry (an entry off a shelf: entry_id, or shelf and title). Confirm with the user before removing a title, a list or a shelf.

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": {
      "what": "<what>"
    },
    "name": "remove"
  }
}

Input Schema

Name	Required	Description
`all`	No
`list`	No
`name`	No
`what`	Yes
`shelf`	No	For shelf_entry: the shelf's name, with title
`title`	No
`prompt`	No	For challenge_pick: the prompt's words or number
`season`	No
`confirm`	No	For shelf: true only after they said yes to deleting it
`episode`	No
`item_id`	No
`slot_id`	No	For challenge_pick: the prompt's id, instead of prompt
`through`	No
`entry_id`	No	For shelf_entry: the entry's id
`event_id`	No
`challenge`	No	For challenge_pick: the challenge's name
`event_date`	No
`media_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedInput schema / properties / media_type / enum

Previous value: -[
-  "book",
-  "movie",
-  "album",
-  "show",
-  "anime",
-  "podcast",
-  "game",
-  "manga",
-  "comic"
-]New value: +[
+  "book",
+  "movie",
+  "album",
+  "show",
+  "anime",
+  "podcast",
+  "game",
+  "manga",
+  "comic",
+  "boardgame"
+]

Changed4 schema fields changedNov 6, 2026

addedInput schema / properties / confirm

Added value: +{
+  "description": "For shelf: true only after they said yes to deleting it",
+  "type": "boolean"
+}

addedInput schema / properties / entry_id

Added value: +{
+  "description": "For shelf_entry: the entry's id",
+  "type": "string"
+}

addedInput schema / properties / shelf

Added value: +{
+  "description": "For shelf_entry: the shelf's name, with title",
+  "type": "string"
+}

changedInput schema / properties / what / enum

Previous value: -[
-  "library",
-  "list_entry",
-  "list",
-  "event",
-  "pin",
-  "episode",
-  "challenge",
-  "challenge_pick"
-]New value: +[
+  "library",
+  "list_entry",
+  "list",
+  "event",
+  "pin",
+  "episode",
+  "challenge",
+  "challenge_pick",
+  "shelf",
+  "shelf_entry"
+]

Changed1 schema field changedNov 5, 2026

changedInput schema / properties / media_type / enum

Previous value: -[
-  "book",
-  "movie",
-  "album",
-  "show",
-  "anime",
-  "podcast",
-  "game",
-  "manga"
-]New value: +[
+  "book",
+  "movie",
+  "album",
+  "show",
+  "anime",
+  "podcast",
+  "game",
+  "manga",
+  "comic"
+]

Changed4 schema fields changedNov 4, 2026

addedInput schema / properties / challenge

Added value: +{
+  "description": "For challenge_pick: the challenge's name",
+  "type": "string"
+}

addedInput schema / properties / prompt

Added value: +{
+  "description": "For challenge_pick: the prompt's words or number",
+  "type": "string"
+}

addedInput schema / properties / slot_id

Added value: +{
+  "description": "For challenge_pick: the prompt's id, instead of prompt",
+  "type": "string"
+}

changedInput schema / properties / what / enum

Previous value: -[
-  "library",
-  "list_entry",
-  "list",
-  "event",
-  "pin",
-  "episode"
-]New value: +[
+  "library",
+  "list_entry",
+  "list",
+  "event",
+  "pin",
+  "episode",
+  "challenge",
+  "challenge_pick"
+]

AddedNov 4, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already cover destructive/idempotent/readOnly, but the description adds genuinely useful context the annotations cannot: cascade semantics ('list (a whole list; its titles stay)', 'shelf (a whole shelf with its entries)', 'challenge ... its titles stay') and a mandatory user-confirmation step for destructive title/list/shelf removals. It does not say whether removals are recoverable or what is returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with the verb and every clause carries information, so there is little waste. However, the single semicolon-and-parenthesis run-on covering ten variants is dense and hard to scan; a list format or one sentence per variant would be more usable.

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

Completeness3/5

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

Given an 18-parameter destructive tool with no output schema, the description covers most variants adequately but leaves several parameters (season, through, episode, and the `list`/`title` pairing for list_entry) undefined in both schema and description. It also never states the outcome of a successful removal, which matters for a destructive operation with no return schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 18 parameters and only 33% schema description coverage, the description carries the bulk of the meaning: media_type+item_id for library, event_id/event_date/all for event, name for challenge, challenge/prompt/slot_id for challenge_pick, name+confirm for shelf, entry_id or shelf+title for shelf_entry. This is well beyond what the schema provides. Minor gaps remain (season, through, episode, list for list_entry are not explained).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Remove') and then enumerates ten distinct resource variants via the `what` enum, each with a one-line characterization. This makes it obvious the tool is a polymorphic delete dispatcher. It does not explicitly distinguish itself from siblings such as delete_item or remove_from_list, which is why it falls short of a 5.

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 gives concrete per-variant selection guidance (which `what` to use and which companion params to supply) plus a clear prerequisite: 'Confirm with the user before removing a title, a list or a shelf,' and 'confirm: true once they said yes' for shelves. What is missing is routing versus the overlapping delete_*/remove_from_* siblings, leaving the agent to guess whether to call this tool or those.

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

All Achriom 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?