Skip to main content
Glama

delete_memory

Deletes a specific memory entry by ID from the workspace or global Memory Vault and removes its index and graph links, keeping stored context accurate.

Instructions

Deletes a specific memory entry by ID from the workspace or global Memory Vault
and removes its index/graph links.

Args:
    memory_id: The ID of the memory entry to delete (e.g. 'mem_a1b2c3d4').
    workspace_dir: Workspace root directory. Empty = engine.default_workspace
           from the config, else the server's current directory.
    scope: Lookup scope ('local', 'global', or 'all'). Default is 'local'.

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": {
      "memory_id": "<memory_id>"
    },
    "name": "delete_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNolocal
memory_idYes
workspace_dirNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.1.2

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does add real behavioral context: deletion also removes index and graph links, and scope 'all' touches both local and global stores. It omits irreversibility, whether confirmation exists, permission requirements, and what happens to dependent graph links on the other side — significant gaps for a destructive mutation with zero annotation coverage.

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

Conciseness4/5

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

The operation and its side effects are front-loaded in one tight sentence, followed by a compact Args block. Slightly verbose fallback prose for workspace_dir, but nothing is wasted.

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?

For a 3-parameter destructive tool with an output schema and no annotations, the definition covers the location semantics, cascade effects, and every parameter. The remaining gap is safety context — irreversibility and any confirmation/permission model — which an agent would reasonably want before calling a delete.

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 0%, so the description must compensate, and it largely does: memory_id gets a format example, workspace_dir gets the empty-string fallback chain (engine.default_workspace, else server CWD), and scope enumerates 'local'/'global'/'all' with a default — enum values the schema does not declare. It stops short of explaining what 'all' does to duplicate IDs across scopes.

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 first sentence gives a specific verb + resource ('Deletes a specific memory entry by ID') and names the two storage locations (workspace vs. global Memory Vault), plus the cascading effect on index/graph links. It doesn't explicitly contrast itself with adjacent tools like clean_snapshots or patch_memory_section, so it falls short of a full 5 on 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 Guidelines3/5

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

Usage is only implied by the verb 'delete' and by the scope parameter documentation. There is no explicit statement of when to delete vs. patch/archive, no prerequisites, and no warning about when 'all' should or should not be used even though it is the riskiest option.

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