Skip to main content
Glama
Sign In
xdragonjia

leafmem

by xdragonjia
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

memory_govern

Manage scoped memory records by updating, deleting, pinning, superseding, or attributing recall usefulness to control decay and keep agent memory relevant.

Instructions

Manage memory: update or delete records (explicit scope required), attribute recall usefulness, or pin/unpin a record against decay.

Input Schema

NameRequiredDescriptionDefault
idNo
kindNo
tagsNo
actionYes
pinnedNo
sourceNo
contentNo
outcomeNo
scopeIdNo
summaryNo
metadataNo
responseNo
recordIdsNo
scopeTypeNo
confidenceNo
importanceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.26
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "update",
-  "delete",
-  "attribute",
-  "pin"
-]New value: +[
+  "update",
+  "delete",
+  "attribute",
+  "pin",
+  "supersede"
+]
  2. First observedv0.3.2

TDQS

C2.4/5.0
Behavior2/5

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

Since there are no annotations, the description must carry the behavioral burden, but it fails to provide critical operational context. While it mentions actions are taken 'against decay,' it does not explain the operational meaning of 'decay,' nor does it specify permissions or error handling necessary for a complex mutation tool.

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?

The definition is a single, efficient sentence that front-loads the main function ('Manage memory'). It effectively lists the five distinct operational modes, ensuring the agent understands the tool's breadth without unnecessary fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is highly complex, involving 16 parameters and five distinct operational states governed by an 'action' enum. A single summary sentence is grossly insufficient to guide an agent, as it does not explain the required dependencies between the 'action' and the necessary values for other fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage and 16 parameters, the description adds almost no semantic value. It refers vaguely to an 'explicit scope required,' but provides zero context or definition for the complex parameters like 'confidence,' 'outcome,' or 'metadata.' The schema must carry nearly 100% of the semantic load.

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 clearly defines the resource managed (memory records) and the general purpose (governance/management). It enumerates the primary functional categories: update, delete, attribute, and pin/unpin. While 'manage memory' is broad, the list of specific actions makes the intent unambiguous.

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

Usage Guidelines2/5

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

The description provides only one operational guideline: 'explicit scope required,' which addresses invocation constraints. It fails to provide comparative usage guidance, leaving the agent to guess when to use this tool versus its sibling, `memory_organize` or `memory_write`.

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