Skip to main content
Glama
po4erk91

Thread Keeper

by po4erk91
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

core_set

Idempotent

Upsert a core-memory entry to keep critical project facts visible in agent briefs, sorted by priority for shared, cross-session context.

Instructions

Upsert a core-memory entry. ALWAYS shown in brief, sorted by priority DESC.

Use sparingly — this is the 'what new-claude must know' surface, not a note store. Good: 'project_root=/Users/.../ai-memory'. Bad: 'today we tried X'. priority 0-100 (higher = shown first). content capped 1KB.

Input Schema

NameRequiredDescriptionDefault
keyYes
contentYes
priorityNo
memory_scopeNoproject

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.19.1
    • addedInput schema / properties / memory_scope
      Added value: +{
+  "default": "project",
+  "title": "Memory Scope",
+  "type": "string"
+}
  2. First observedv0.13.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations cover the safety profile (idempotent upsert, non-destructive), so the bar is lower. The description still adds real behavior: 'ALWAYS shown in brief, sorted by priority DESC' and the 1KB content cap, which are consequences an agent cannot infer from annotations or schema.

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 core action, then behavior and usage guidance. The examples earn their place by defining the intended granularity; the only minor friction is the parenthetical density in the back half.

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?

An output schema exists, so return values needn't be described, and the description covers usage, key behaviors, and two parameters. The unexplained memory_scope parameter is the one notable gap for a 4-param upsert tool.

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 0%, so the description must carry the load and it partially does: it documents priority range/direction and the content size limit. However, 'key' and 'memory_scope' (default 'project') receive no explanation, leaving half the parameters undocumented.

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?

States a specific verb+resource combination ('Upsert a core-memory entry') and clarifies the distinction from a general note store. It does not explicitly name sibling tools like core_get/core_list/core_remove, but the scope is 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?

Gives explicit when/when-not guidance with concrete good/bad examples and the warning 'Use sparingly... not a note store'. It stops short of naming an alternative tool to use instead (e.g., note), which keeps it from a 5.

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