Skip to main content
Glama

Forget / retract (kept in history for audit)

forget

Retract a fact so it is no longer returned as current while remaining in audit history; use it when information is removed without a replacement.

Instructions

Retract a fact — a removal with no replacement. Unlike additive stores, this actually retires it so it stops being returned as current (kept in history for audit). Examples: 'We dropped Sentry', 'Alice left the Platform team', 'we no longer support IE11'.

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": {
      "text": "<text>"
    },
    "name": "forget"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
run_idNo
user_idNodefault
agent_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds the crucial reason: the fact is retired yet "kept in history for audit," which reconciles a removal operation with destructiveHint=false. That is genuine value beyond the structured fields, though it leaves idempotency (annotation says false) and any auth/scoping behavior unmentioned.

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 core definition is front-loaded in the first sentence, with the audit note parenthetical and examples following as support. Three examples is slightly more than needed and they are not labeled as illustrating the `text` field, but nothing is redundant filler.

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?

An output schema exists, so return values need not be described, and the audit/retention behavior is covered. However, for a mutation with four undocumented parameters at 0% coverage, the definition says nothing about run/agent scoping or whether a retraction is confirmable, leaving real gaps relative to the tool's complexity.

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

Parameters2/5

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

Schema description coverage is 0% across four parameters, so the description must compensate and largely does not. The examples give a weak hint about the shape of `text`, but `run_id`, `user_id`, and `agent_id` — which determine whose memory is affected — are never explained, leaving scoping semantics entirely to guesswork.

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 effect: "Retract a fact — a removal with no replacement," then explicitly contrasts with "additive stores" and clarifies the observable consequence ("stops being returned as current"). The three examples ('We dropped Sentry', 'Alice left the Platform team', 'we no longer support IE11') let an agent recognize the operation without opening the schema.

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?

The parenthetical "a removal with no replacement" plus "Unlike additive stores" gives clear selection context: this is for retiring a fact when there is nothing to substitute. It stops short of explicitly naming an alternative such as update_memory for the replace case, or stating when not to use it (e.g. superseding a value rather than dropping it).

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