Skip to main content
Glama

delete_account_item

Destructive

Permanently deletes one object of the user's JusticeLibre account: a case file (with all its content), a saved reference, a subfolder, a note, or an AI skill proposal not yet activated (skill, id s_…, p_… or w_…). No recycle bin. confirm=true states the user's explicit agreement; without it, nothing is deleted. Permission supprimer; a reference the AI saved itself can also be removed with permission notes_ia. To keep a trace with a reason instead: update_account_item with set_aside. case_file_title (and subfolder_title for a subfolder) are expected, copied exactly from get_account_item: the user approves by those names; a mismatch refuses the call. Notes: only the AI's own notes are deleted here; notes written by the user are never deleted, edited or set aside by the AI. An element or case file holding notes written by the user is refused (code notes_utilisateur): only the user can delete it, on the site. Requires a JusticeLibre account (OAuth sign-in). get_account_item (kind="case_file") gives the case file with its active instructions (consignes), each labelled with its author, returned as data. Write responses include the case file's active instructions (labelled with their author), returned as data (case_file_instructions).

Example: delete_account_item(what="note", id="n_…", confirm=true)

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>",
      "id": "<id>"
    },
    "name": "delete_account_item"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes"d_…", "e_…", "c_…", "n_…", "s_…"/"p_…"/"w_…", or "b_…".
whatYes"folder", "element" (saved reference), "subfolder", "note", "skill" (AI skill proposal not yet activated) or "bookmark".
confirmNotrue = the user explicitly agreed; otherwise nothing is deleted.
case_file_titleNoexact name of the case file deleted or holding the object, shown to the user for approval; must match, or nothing is deleted. Expected for every kind except skill.
subfolder_titleNowhat="subfolder": exact name of the subfolder deleted; must match.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / case_file_title / description
      Previous value: -"exact name of the case file deleted or holding the object, shown to the user for approval; must match, or nothing is deleted. Always fill it (not for skill)."New value: +"exact name of the case file deleted or holding the object, shown to the user for approval; must match, or nothing is deleted. Expected for every kind except skill."
  2. Changed3 schema fields changed
    • changedInput schema / properties / id / description
      Previous value: -"\"d_…\", \"e_…\", \"c_…\", \"n_…\", or \"s_…\"/\"p_…\"/\"w_…\"."New value: +"\"d_…\", \"e_…\", \"c_…\", \"n_…\", \"s_…\"/\"p_…\"/\"w_…\", or \"b_…\"."
    • changedInput schema / properties / what / description
      Previous value: -"\"folder\", \"element\" (saved reference), \"subfolder\", \"note\" or \"skill\" (AI skill proposal not yet activated)."New value: +"\"folder\", \"element\" (saved reference), \"subfolder\", \"note\", \"skill\" (AI skill proposal not yet activated) or \"bookmark\"."
    • changedInput schema / properties / what / enum
      Previous value: -[
      -  "folder",
      -  "element",
      -  "subfolder",
      -  "note",
      -  "skill"
      -]New value: +[
      +  "folder",
      +  "element",
      +  "subfolder",
      +  "note",
      +  "skill",
      +  "bookmark"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / id / description
      Previous value: -"\"d_…\", \"e_…\", \"c_…\", \"n_…\", or \"s_…\"/\"p_…\"."New value: +"\"d_…\", \"e_…\", \"c_…\", \"n_…\", or \"s_…\"/\"p_…\"/\"w_…\"."
  4. Changed2 schema fields changed
    • addedInput schema / properties / case_file_title
      Added value: +{
      +  "default": "",
      +  "description": "exact name of the case file deleted or holding the object, shown to the user for approval; must match, or nothing is deleted. Always fill it (not for skill).",
      +  "title": "Case File Title",
      +  "type": "string"
      +}
    • addedInput schema / properties / subfolder_title
      Added value: +{
      +  "default": "",
      +  "description": "what=\"subfolder\": exact name of the subfolder deleted; must match.",
      +  "title": "Subfolder Title",
      +  "type": "string"
      +}
  5. Changed3 schema fields changed
    • changedInput schema / properties / confirm / description
      Previous value: -"true = l'utilisateur a donné son accord ; sinon rien n'est supprimé."New value: +"true = the user explicitly agreed; otherwise nothing is deleted."
    • changedInput schema / properties / id / description
      Previous value: -"« d_… », « e_… », « c_… » ou « n_… »."New value: +"\"d_…\", \"e_…\", \"c_…\", \"n_…\", or \"s_…\"/\"p_…\"."
    • changedInput schema / properties / what / description
      Previous value: -"\"folder\", \"element\", \"subfolder\" ou \"note\"."New value: +"\"folder\", \"element\" (saved reference), \"subfolder\", \"note\" or \"skill\" (AI skill proposal not yet activated)."
  6. Added
  7. Removed
  8. Changed1 schema field changed
    • changedInput schema / properties / what / enum
      Previous value: -[
      -  "folder",
      -  "element",
      -  "subfolder",
      -  "note"
      -]New value: +[
      +  "folder",
      +  "element",
      +  "subfolder",
      +  "note",
      +  "skill"
      +]
  9. Changed8 schema fields changed
    • addedInput schema / properties / confirm
      Added value: +{
      +  "default": false,
      +  "description": "true = l'utilisateur a donné son accord ; sinon rien n'est supprimé.",
      +  "title": "Confirm",
      +  "type": "boolean"
      +}
    • removedInput schema / properties / confirmation
      Removed value: -{
      -  "default": false,
      -  "description": "Doit valoir true, après accord explicite de l'utilisateur ; sinon rien n'est supprimé.",
      -  "title": "Confirmation",
      -  "type": "boolean"
      -}
    • changedInput schema / properties / id / description
      Previous value: -"Identifiant de l'objet (« d_… », « e_… », « c_… » ou « n_… »)."New value: +"« d_… », « e_… », « c_… » ou « n_… »."
    • removedInput schema / properties / quoi
      Removed value: -{
      -  "description": "\"dossier\", \"element\", \"sous_dossier\" ou \"note\".",
      -  "enum": [
      -    "dossier",
      -    "element",
      -    "sous_dossier",
      -    "note"
      -  ],
      -  "title": "Quoi",
      -  "type": "string"
      -}
    • addedInput schema / properties / what
      Added value: +{
      +  "description": "\"folder\", \"element\", \"subfolder\" ou \"note\".",
      +  "enum": [
      +    "folder",
      +    "element",
      +    "subfolder",
      +    "note"
      +  ],
      +  "title": "What",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "quoi",
      -  "id"
      -]New value: +[
      +  "what",
      +  "id"
      +]
    • changedInput schema / title
      Previous value: -"compte_supprimer_objetArguments"New value: +"delete_account_itemArguments"
    • changedOutput schema / title
      Previous value: -"compte_supprimer_objetDictOutput"New value: +"delete_account_itemDictOutput"
  10. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds substantial context beyond them: no recycle bin, confirm=true is a hard gate ("without it, nothing is deleted"), permission requirements (supprimer, notes_ia), a title-mismatch refusal path, and a named refusal code (notes_utilisateur). That is the kind of pre-call consequence and failure-mode disclosure a mutation tool needs.

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?

The core consequence and the confirm gate are front-loaded, but the text is a dense single block that re-explains case-file instructions twice (once pointing at get_account_item, once about write responses), which is redundant given an output schema exists. It is informative but not efficiently structured.

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, multi-kind delete with a permission model, refusal codes, and an approval-by-name protocol, the description covers consequences, prerequisites, failure modes, the write-side return context, and an invocation example. Nothing needed to call it safely 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%, so the baseline is 3, but the description adds real meaning: case_file_title/subfolder_title must be copied exactly from get_account_item because "the user approves by those names; a mismatch refuses the call," and confirm is framed as the user's explicit agreement rather than a generic flag. Minor duplication of what the schema already says about confirm keeps it from a 5.

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 deletes one object of the user's JusticeLibre account") and then enumerates the deletable kinds (case file, saved reference, subfolder, note, skill proposal), so an agent can distinguish it from siblings like update_account_item without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit alternative and the condition that selects it: "To keep a trace with a reason instead: update_account_item with set_aside." It also states hard exclusions (user-written notes are never deleted, edited or set aside by the AI; such elements must be deleted by the user on the site), which is genuine when-not guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources