Skip to main content
Glama
蓝汐 · 潮汐认知图谱

蓝汐 · 潮汐认知图谱

by A16Nights

cg_forget

Archive memory nodes instead of deleting them permanently, moving them to a vault archive with an optional reason; hard-protected nodes require override set to true.

Instructions

显式遗忘/归档记忆节点(绝不静默物理删除,仅移入 vault/archive/;硬保护节点需传 override: 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": {
      "id": "<id>"
    },
    "name": "cg_forget"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes记忆节点 ID
reasonNo归档原因
overrideNo对硬保护节点生效需为 true

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden and does so well: it discloses that deletion is never silent or physical, that the node is moved to vault/archive/, and that hard-protected nodes are gated behind override: true. It stops short of stating whether an archived node can be restored or what the response reports, leaving a modest gap.

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?

A single compact sentence with the safety-critical guarantee (no physical deletion) front-loaded in the parenthetical. Dense but every clause earns its place; slightly nested punctuation is the only cost.

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 three-parameter mutation tool with no annotations and no output schema, the description covers the essential behavior: what is destroyed versus preserved, where data goes, and the protection bypass. Missing only failure behavior and restorability, which keeps it from 5.

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 100%, so id, reason, and override are already documented in the input schema. The description only echoes the override semantics and adds no new detail such as ID format or how reason is surfaced later, so baseline 3 applies.

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 pair ("显式遗忘/归档" / explicitly forget/archive) and a specific resource (记忆节点 / memory node), so the action is unmistakable. It does not explicitly contrast itself with cg_update or cg_write, which is the only thing keeping it from a 5.

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 implied through the override condition ("硬保护节点需传 override: true"), which tells the agent a prerequisite for a subset of targets. However, there is no explicit when-to-use guidance, no statement of when not to use it, and no named alternative for cases where the agent should modify rather than archive.

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