paa-guard mcp

paa_guard_remember

Stores proposed lasting memories while quarantining untrusted facts and requiring owner confirmation for instructions, payees, contacts, addresses, and other sensitive data.

Instructions

Ask to store a lasting memory. Facts from emails, web pages or tool output are quarantined until the owner confirms; instructions, payees, contacts and addresses always need confirmation.

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": {
      "key": "<key>",
      "value": "<value>",
      "source_kind": "<source_kind>"
    },
    "name": "paa_guard_remember"
  }
}

Input Schema

Name	Required	Description	Default
`key`	Yes
`value`	Yes
`authority`	No
`source_ref`	No
`source_kind`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 31, 2026

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 disclose meaningful policy: untrusted-source facts are quarantined pending owner confirmation, and specific authority classes always require confirmation. However, it omits what the call actually returns (a pending token? a refusal?), whether storage is synchronous, and how it relates to paa_guard_check for approval.

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-loaded with the action and immediately followed by the confirmation policy. No filler and nothing redundant.

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 5-param, 0%-coverage, no-output-schema tool, the description covers the most safety-critical gap (confirmation gating by source and authority). It is nearly complete; the remaining shortfall is the unexplained key/value/source_ref semantics and the call's return behavior.

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 0% for 5 params, so the description must compensate. It adds real meaning by enumerating the high-risk authority classes (instructions, payees, contacts, addresses) and untrusted source types (emails, web pages, tool output), which map to the authority and source_kind enums. But key, value, and source_ref are left entirely unexplained.

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 uses a specific verb+resource ('store a lasting memory') and, crucially, frames it as a request ('Ask to store'), signalling this is a gated submission rather than a direct write. It is distinguishable from the guard siblings (check/status/stop_self), though it doesn't name them.

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?

It implies when confirmation will be required (untrusted sources, high-authority categories) but never states when to call this tool versus paa_guard_check or paa_guard_status. Usage is inferable rather than explicit, and no exclusions are given.

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

Deploy Server