Skip to main content
Glama

krusch_context_remember

Store facts, decisions, lessons, blockers, and steering nuggets as persistent memory with tags, provenance, and near-duplicate warnings to keep AI coding agents aligned across sessions.

Instructions

Unified write API for episodic memory and persistent steering nuggets. Includes automatic near-duplicate detection and provenance tracking.

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

Input Schema

NameRequiredDescriptionDefault
keyNoOptional key to store as a persistent steering nugget
tagsNoOptional descriptive tags
forceNoIf true, bypasses near-duplicate warnings
contentYesThe fact, lesson, decision, or invariant to remember
projectNoTarget project
categoryNoClosed category taxonomylesson
provenanceNoProvenance & KruschNexus span-grounding metadata

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.2

TDQS

B3.2/5.0
Behavior3/5

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

Annotations only declare the mutation profile (readOnly=false, destructive=false, non-idempotent). The description adds real value beyond that by disclosing automatic near-duplicate detection and provenance tracking, which tells an agent its writes may be flagged rather than silently accepted. It still does not say whether a duplicate causes rejection or just a warning, nor what the write returns or how to correct a bad memory.

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?

Two tight sentences, front-loaded with the core verb and resource, then the behavioral extras. 'Unified' is mild filler but the rest earns its place.

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

Completeness3/5

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

For a 7-parameter tool with a nested provenance object and no output schema, the description is thin: it never explains what comes back (an id, a duplicate warning, a dedup decision), so an agent cannot chain the result into follow-up calls. The schema carries the parameter burden, but the post-write behavior described in prose ('near-duplicate detection') is left unresolved.

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 100%, so every parameter including the nested provenance object is already documented in structured form. The description's only supplementary meaning is framing key as the switch between episodic memory and persistent steering nuggets, which is a modest addition over the schema's own wording.

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 names a concrete action (write) and its object (episodic memory records and persistent 'steering nuggets'), and distinguishes the two storage modes via the key parameter. It stops short of contrasting itself with the sibling krusch_context_revise, so an agent still has to guess the write-vs-revise boundary.

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?

There is no when-to-use or when-not-to-use guidance and no named alternative, even though krusch_context_revise and krusch_context_retrieve sit in the same family. The reader can infer 'this is how you store things,' but nothing states when to revise an existing entry instead of remembering a new one.

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