Skip to main content
Glama
MerakOsiris

MemoryGuard

by MerakOsiris
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memoryguard_memory_write

Save durable facts, preferences, project decisions, or procedures on request. Writes locally, organizing duplicates and conflicts for reliable recall.

Instructions

Use when user explicitly asks to retain a durable fact, preference, project decision, or procedure. Do not use for raw transcripts or temporary task notes. Writes locally and may organize duplicates or conflicts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyYesmemory content
kindNooptional kind override; omit for native classification
audienceNomandatory-rule assignments; omitted always defaults to the trusted current agent
metadataNooptional metadata from agent
priorityNostable ordering within the mandatory rule package
write_policyNooptional write policy; propose_only creates a low_confidence candidate, while omission uses automatic organization
idempotency_keyNooptional retry key bound to content, metadata, kind and policy
injection_policyNorelevant participates in task recall; always is a mandatory rulerelevant
agent_instance_idNooptional identity consistency check; trusted MCP environment is authoritative

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.7.12
    • changedInput schema / properties / kind / description
      Previous value: -"override kind (default: auto-classify). Valid: preference|fact|project|procedure|episode|correction"New value: +"optional kind override; omit for native classification"
    • addedInput schema / properties / kind / enum
      Added value: +[
+  "preference",
+  "fact",
+  "project",
+  "procedure",
+  "episode",
+  "correction"
+]
    • changedInput schema / properties / write_policy / description
      Previous value: -"write policy: auto_accept (default) | auto_quarantine_on_risk | propose_only. propose_only creates a low_confidence candidate without modifying existing memories"New value: +"optional write policy; propose_only creates a low_confidence candidate, while omission uses automatic organization"
  2. First observedv0.7.8

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already indicate a non-read-only, non-idempotent, non-destructive operation. The description adds value by disclosing local write behavior and the potential to organize duplicates or conflicts, which goes beyond the annotation flags. No contradiction found.

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 sentences with zero filler. The primary use case is front-loaded, and the exclusion and behavioral notes are placed efficiently. Every sentence earns its place.

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?

The description covers purpose, usage boundaries, and key behavioral traits. With a high-coverage schema and no output schema, it provides sufficient context for an agent to call the tool correctly. Minor gaps like success return values are acceptable given the lack of an output schema.

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 all parameters are documented. The description enriches the meaning of the primary parameter 'body' by providing concrete examples of durable content (facts, preferences, decisions, procedures), which goes beyond the schema's generic 'memory content'.

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?

The description clearly states the action ('retain a durable fact, preference, project decision, or procedure') and the resource (durable memory). It also differentiates from siblings by explicitly excluding raw transcripts and temporary task notes, making its scope unambiguous.

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?

Provides explicit triggers ('when user explicitly asks to retain') and exclusions ('do not use for raw transcripts or temporary task notes'). While it doesn't name alternative tools like memory_read or memory_update, the guidance is clear enough for an agent to decide when to invoke this write tool.

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

Deploy Server

Other Tools