Skip to main content
Glama

Create a memory share link

create_memory_share

Use this when the user asks to share memories with another person or another MemoryRouter account, for example 'make a share link for everything about project X'. Creates a link and a password that let someone else import a frozen copy of memories from the connected vault into their own vault. Neither side ever sees the other's memory key. The first call (no confirmation) only previews how many memories would be shared and never creates a link. After the user confirms the preview, call again with the same arguments and the exact confirmation phrase. Defaults: one-time use and a 7 day expiry. Prefer scope 'selected' with focused queries over sharing a whole vault.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_memory_share"
  }
}

Input Schema

NameRequiredDescriptionDefault
usesNo'once' (default) lets one account import. 'multi' lets many accounts import.
labelNoOptional name the receiver sees.
scopeNo'selected' shares memories matching the queries. 'all' shares the whole vault.
queriesNoSearch phrases that pick what to share. Required for scope 'selected'.
max_usesNoOptional exact number of accounts that may import.
no_expiryNoSet true for a link that never expires.
thresholdNoSimilarity threshold from 0 to 1 for selected memories. Default 0.6.
confirmationNoExact phrase, only after the user has seen the preview and confirmed.
expires_in_daysNoDays until the link expires. Default 7.

Output Schema

NameRequiredDescriptionDefault
idNo
linkNo
countNo
scopeNo
createdYes
previewNo
max_usesNo
passwordNo
expires_atNo
expires_in_daysNo
estimated_tokensNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false; the description goes well past them. It discloses the security model (neither side sees the other's memory key), the frozen-copy semantics, the non-obvious two-phase preview-then-confirm protocol where the first call 'never creates a link,' and the default one-time/7-day expiry. That is precisely the behavioral context an agent needs before invoking.

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?

Front-loaded with the trigger condition, then the mechanics, then the two-phase flow, then defaults and preference—a sensible priority order with no filler. It is dense and runs long, but nearly every clause carries information an agent could otherwise get wrong.

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?

For a 9-parameter, open-world mutation tool with an output schema and annotations, this covers the pieces the structured fields cannot: the preview/confirm protocol, the security guarantee, expiry defaults, and scope preference. 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 the baseline is 3, but the description adds real meaning to two non-obvious parameters: it explains that the same arguments must be repeated on the confirmation call and that 'confirmation' must be the exact phrase, and it restates the one-time/7-day defaults while steering scope toward 'selected'. Remaining parameters like threshold and max_uses get no extra guidance beyond the schema.

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 resource: it 'Creates a link and a password' that let someone 'import a frozen copy of memories from the connected vault into their own vault.' That framing cleanly separates it from siblings like import_memory_share, revoke_memory_share, and list_memory_shares, which act on existing shares rather than minting one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Opens with an explicit trigger ('Use this when the user asks to share memories...'), supplies a concrete example utterance, and adds a preference rule ('Prefer scope selected with focused queries over sharing a whole vault'). It also spells out the two-call sequencing and the condition that selects the second call: only after the user confirms the preview.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources