Skip to main content
Glama
MemoryShield+ Agent Plugin

MemoryShield+ Agent Plugin

by GFDDFDGHJ

memoryshield_remember

Stores original messages in a user's persistent memory under a stable session ID, preserving conversation history for personalized cross-session recall.

Instructions

Store original messages in this user's persistent memory.

Use a stable session_id for one conversation or workflow. A batch permits 20 messages, 32,000 characters per message and 64,000 characters total. Reuse request_id and identical content when retrying. A fresh call without request_id creates a new write. This calls the backend's paid Add models.

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": {
      "messages": "<messages>",
      "session_id": "<session_id>"
    },
    "name": "memoryshield_remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
messagesYes
request_idNo
session_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations it discloses batch caps (20 messages, 64,000 characters total, a total cap absent from the schema), the request_id dedup/retry contract that softens idempotentHint=false, and the cost warning that this invokes the backend's paid Add models. The cost and retry semantics are exactly the kind of behavior an agent cannot infer from structured fields.

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 purpose is front-loaded in the first sentence and each following sentence carries a distinct fact (session scoping, limits, retry, cost). The line breaks and spacing add a little visual noise but no genuinely redundant content.

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?

Given existing annotations and an output schema, the description covers the aspects an agent most needs: cost, batch limits, scoping, and retry safety. It stops short of describing failure modes or deduplication on content alone, but nothing essential for a correct call 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?

With reported schema description coverage at 0%, the description carries the burden and mostly succeeds: it explains session_id scoping, request_id retry semantics, and the meaning of the messages batch limits. The role and timestamp fields remain unexplained, which is a minor residual gap rather than a blocking one.

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 description opens with a specific verb and resource: 'Store original messages in this user's persistent memory', which is concrete enough that an agent can distinguish a write tool from the read-oriented siblings memoryshield_recall and memoryshield_status. It does not name those siblings explicitly, so sibling differentiation is implied rather than stated.

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?

It gives clear operational guidance: use a stable session_id per conversation or workflow, reuse request_id plus identical content when retrying, and note that an omission of request_id produces a new write. That covers the main decision points for calling it correctly, though it never states when to prefer this tool over other memory operations.

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