Skip to main content
Glama

krusch_context_remember

Persist durable rules, architectural decisions, bug root causes, lessons, and blockers with optional file/span provenance so coding agents retain cross-session context.

Instructions

Persist a durable rule, architectural decision, bug root-cause, lesson, or blocker with optional file/span provenance.

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": {
      "category": "<category>",
      "content": "<content>"
    },
    "name": "krusch_context_remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
contentYesDurable rule or decision statement
categoryYes
provenanceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.1

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnly=false, destructive=false, openWorld=false, and idempotent=false. The description adds that records are durable and that provenance is optional, but it never explains what non-idempotency means in practice (repeated calls likely create duplicate entries) or where/how the persisted memory resurfaces later.

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?

A single front-loaded sentence with no filler; the enumeration earns its space because each item clarifies an enum value. Slightly dense but well-structured.

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 3-parameter create-style tool with annotations covering the safety profile and no output schema, this is close to sufficient. The residual gap is the undocumented nested provenance structure and the lack of any note on deduplication given idempotentHint=false.

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 coverage is only 33% — only 'content' is documented — but the description compensates partially by expanding the five category values into meaningful concepts. The nested provenance object (file, locator, quoted_sentence) is only alluded to as 'file/span provenance', leaving 'quoted_sentence' and locator syntax unexplained.

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 verb 'Persist' plus the enumerated resource types (durable rule, architectural decision, bug root-cause, lesson, blocker) map directly onto the category enum, so an agent knows exactly what this tool records. It does not, however, distinguish itself from similarly named siblings such as krusch_fs_remember_on_page or krusch_context_revise.

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 word 'durable' hints at long-lived knowledge as opposed to scratch notes, but there is no explicit when-to-use statement, no prerequisite, and no mention of alternatives for page-scoped or revising existing memories. The agent must infer routing from sibling names alone.

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