Skip to main content
Glama
vbcherepanov

total-agent-memory

memory_delete

DestructiveIdempotent

Delete a knowledge record: soft-delete hides it from search and vectors, while hard=true permanently erases it, its versions, derived rows, and raw call-log text.

Instructions

Delete a knowledge record. By default a soft delete: the record leaves search results and vectors but stays in the database. hard=true erases it for good, with its earlier versions, derived rows and its text in the raw call log (use for personal data or anything that must not be kept).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesKnowledge record ID to delete
hardNoErase permanently instead of hiding; cannot be undone

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv14.7.0
    • addedInput schema / properties / hard
      Added value: +{
      +  "default": false,
      +  "description": "Erase permanently instead of hiding; cannot be undone",
      +  "type": "boolean"
      +}
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the destructiveHint/idempotentHint annotations by disclosing exactly what each mode touches: soft delete removes the record from search results and vectors while leaving it in the database, and hard delete erases earlier versions, derived rows, and the raw call-log text. This is precisely the kind of destructive-scope detail the annotations cannot express.

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?

Two tight sentences, front-loading the default safe behavior before the destructive option, with zero filler. Every clause carries information the agent needs.

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?

With no output schema and annotations already covering the safety profile, the description supplies the remaining essentials for a 2-param mutation tool: default behavior, hard-mode consequences, and a use case. Nothing needed to call it correctly 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 baseline is 3, but the description adds meaning beyond the schema's 'erase permanently instead of hiding': it enumerates the collateral (prior versions, derived rows, raw log text) and clarifies the default soft-delete behavior. That is genuine added value over the terse schema text.

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) and resource (knowledge record), and crisply splits the operation into soft vs hard semantics. It does not, however, differentiate itself from the overlapping sibling memory_forget, so it stays at a clear-but-unrouted 4.

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 a concrete condition for the destructive path ('use for personal data or anything that must not be kept') and defines the default behavior, which is real usage context. It names no sibling alternative (e.g. memory_forget) and states no when-not, so it stops short of a 5.

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