Skip to main content
Glama
persistent-memory-mcp

persistent-memory-mcp

Remember a source

memory_remember

Store a new fact, decision, document or procedure the user stated or confirmed as a source, returning an artifact_id and ref. Use it to capture confirmed information, not your own conclusions or corrections.

Instructions

Store a new fact, decision, document or procedure the user stated or confirmed, as a source. Do not use it for your own conclusions (memory_derive), for lessons after a task (memory_learn), or to change something already stored (memory_correct). Returns artifact_id and ref. Sending the same source_id with the same text again changes nothing; with a different text it is refused with version_conflict.

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": {
      "text": "<text>"
    },
    "name": "memory_remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoobservation for a fact, document for a text, procedure for how to do something, task, feedback, or hypothesis for a guess nobody confirmed.
textYesSelf-contained statement, with its date if known.
aliasesNoShort names to find it again.
source_idNoStable name you choose, such as 'db-port', to correct or withdraw it later. Leave out to get one.
confidenceNoDeclared, not computed. Leave out unless the user gave one.
valid_fromNoUTC time it starts to apply, e.g. 2026-01-31T00:00:00Z. Leave out unless the user gave one; by default it applies now.
valid_untilNoUTC time after which it no longer applies. Leave out unless the user gave one.
preconditionsNoExact conditions a search must supply to see it. Leave out unless the user said it only holds under a condition: a search without these conditions will not return it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

With annotations already declaring destructiveHint=false and openWorld=false, the description adds real behavioral detail: it discloses the return values (artifact_id, ref) and the source_id replay semantics — identical text is a no-op, different text is refused with version_conflict. Minor tension with idempotentHint=false (the described same-text behavior is effectively idempotent), but not a direct contradiction since differing text yields a refusal rather than a silent write.

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?

Three tight sentences with zero filler: purpose first, exclusions second, return/conflict semantics last. Every clause carries information an agent would otherwise have to guess.

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?

Despite eight parameters, a nested object, and no output schema, the description covers the decision boundary, the return shape, and the failure mode. Nothing an agent needs in order 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 baseline is 3, but the description adds meaning the schema does not: it explains why source_id matters (reuse to correct or withdraw later) and what happens on reuse with conflicting text. Other parameters (kind, confidence, validity windows, preconditions) are left entirely to the schema, which is acceptable given full coverage.

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 ('Store a new fact, decision, document or procedure ... as a source') and pins the scope to what the user 'stated or confirmed'. It then names the three siblings it is not — memory_derive, memory_learn, memory_correct — so an agent can distinguish it without opening any schema.

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?

Provides explicit when-not guidance mapped to alternatives: conclusions go to memory_derive, post-task lessons to memory_learn, edits to memory_correct. The positive condition ('user stated or confirmed') plus the three named exclusions leaves little inference needed.

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