Skip to main content
Glama

Import memories (PMM)

memory_import

Import a PMM v1 export to restore memory content and scope, with options to skip duplicate records or overwrite existing ones. Embeddings and graphs are not carried over.

Instructions

Import a PMM v1 payload from memory_export. Content and scope carry over; embeddings and graphs do not.

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": {
      "data": "<data>"
    },
    "name": "memory_import"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataYesSerialized PMM export (json or jsonl text)
merge_strategyNoHow to treat records that already exist (default skip_duplicates)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.8.0
    • changedInput schema / properties / data / description
      Previous value: -"Serialized export payload"New value: +"Serialized PMM export (json or jsonl text)"
    • addedInput schema / properties / merge_strategy / description
      Added value: +"How to treat records that already exist (default skip_duplicates)"
  2. First observedv0.6.3

TDQS

A3.6/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, so the mutating, repeat-hostile nature is covered structurally. The description does add real value by disclosing that embeddings and graphs are dropped while content and scope survive. What it omits is that merge_strategy=overwrite can replace existing records, an asymmetry that sits awkwardly against destructiveHint=false and leaves the agent without a data-loss warning.

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 with the action and its source front-loaded and the lossy-import caveat immediately after. No filler, and every clause carries information the agent needs.

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 two-parameter import with full schema coverage, no output schema, and annotations covering the safety profile, the description supplies the format, the source tool, and the fidelity limits. It falls just short of complete because it never says what the tool returns or what happens on a malformed payload, and it leaves the overwrite hazard implicit.

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 description coverage is 100% and the merge_strategy enum is documented with its default in the schema, so the baseline of 3 applies. The description adds nothing parameter-specific beyond the general statement that content and scope persist, which is relevant context but not a refinement of either parameter.

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?

Specific verb (Import) plus specific resource (a PMM v1 payload) and an explicit provenance constraint (from memory_export), which cleanly separates it from memory_add and memory_export among the siblings. The only softness is that 'PMM' is an unexplained acronym, so an agent unfamiliar with the format gets no gloss on what a v1 payload actually is.

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?

Naming memory_export implies the round-trip use case, so usage is inferable rather than stated. However there is no explicit when-to-use versus memory_add or memory_consolidate, and no guidance on when skip_duplicates vs overwrite is appropriate, which is the one decision the agent actually has to make.

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