Skip to main content
Glama

Delete note

bm_delete
DestructiveIdempotent

Delete a Basic Memory note or directory permanently, optionally only if its checksum still matches the revision you read; directory removal requires recursive=true.

Instructions

Delete a Basic Memory note (identifier) or a directory (path). A directory delete removes every file under it and needs recursive=true. Pass expected_checksum (from bm_read) to delete a note only if it is still the revision you read. A note that does not exist is an error. This cannot be undone.

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": {
      "project": "<project>"
    },
    "name": "bm_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoThe directory to delete, with everything in it.
projectYesRequired project name, 'workspace/project', or project external id. Discover projects with bm_project(command='list'). Paths are relative to this project; a qualified path must agree with it.
recursiveNoRequired true to delete a directory and everything under it.
identifierNoThe note to delete: a path, permalink, memory:// URL or exact title.
output_formatNotext
expected_checksumNoDelete the note only while it is still this revision (from bm_read).

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • removedInput schema / properties / project / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / properties / project / default
      Removed value: -null
    • changedInput schema / properties / project / description
      Previous value: -"Project name, 'workspace/project', or project external id. Omit to use the default project."New value: +"Required project name, 'workspace/project', or project external id. Discover projects with bm_project(command='list'). Paths are relative to this project; a qualified path must agree with it."
    • addedInput schema / properties / project / minLength
      Added value: +1
    • addedInput schema / properties / project / type
      Added value: +"string"
    • addedInput schema / required
      Added value: +[
      +  "project"
      +]
    • changedOutput schema / properties / result / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  {
      -    "type": "string"
      -  }
      -]New value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "additionalProperties": true,
      +    "type": "object"
      +  }
      +]
  2. Addedv0.24.1

TDQS

A4/5.0
Behavior4/5

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

Adds meaningful behavior beyond the annotations: irreversibility is stated plainly, directory deletion is gated on `recursive=true`, and a missing note raises an error rather than silently succeeding. The checksum-gated delete is real context an agent cannot get from destructiveHint alone; only cross-parameter conflict behavior is missing.

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?

Four short sentences, front-loaded with the two deletion modes, followed by preconditions and the irreversibility warning as a closing emphasizer. Nothing is repeated from the schema verbatim and no sentence is filler.

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?

Output schema exists, so return values need not be explained, and the annotations already declare destructive/idempotent semantics. For a destructive mutation the description covers modes, gating flags, existence errors, and irreversibility; only permission/auth expectations and the identifier-vs-path precedence are unstated.

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 coverage is high (83%) and each parameter already carries its own description, so the schema carries the load. The description reinforces the `recursive` requirement and the provenance of `expected_checksum` (from bm_read) but adds little new syntax or format guidance beyond the schema, making 3 the correct baseline.

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?

States a specific verb (Delete) against two clearly named resource modes — a note via `identifier` or a directory via `path` — which is the main ambiguity an agent would face. It does not contrast itself with sibling mutators like bm_edit or bm_move, so it stops short of full sibling differentiation.

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 explicit conditional usage: use `recursive=true` to delete a directory, pass `expected_checksum` from bm_read for revision-guarded deletes. It does not say when to prefer a different tool (e.g., moving or editing instead of deleting) or explicitly state what happens if both `identifier` and `path` are supplied.

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