Skip to main content
Glama

krusch_context_revise

DestructiveIdempotent

Revise persistent project memory by superseding stale knowledge with lineage or invalidating obsolete rules with a mandatory reason, keeping AI agent context accurate across sessions.

Instructions

Unified knowledge revision API. Supports temporal superseding (updating stale knowledge with lineage) and explicit invalidations (revoking obsolete rules with mandatory reason).

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": {
      "action": "<action>"
    },
    "name": "krusch_context_revise"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoKey of nugget to forget when action is forget_nugget
actionYesRevision action to perform
reasonNoMandatory justification when invalidating a memory
contentNoNew authoritative content when superseding
projectNoTarget project
categoryNoOptional category update
target_idNoTarget memory ID (for supersede or invalidate)
provenanceNoOptional provenance metadata

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.2

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description usefully adds that supersede preserves lineage and that invalidation requires a mandatory reason, but it does not disclose whether forget_nugget is permanent or what data is lost.

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 dense, front-loaded sentences with no filler; the 'unified' framing up front followed by the two modes is easy to scan. Slight loss because the parenthetical detail crowds out the third action.

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?

With 8 parameters, three actions, no output schema and destructive semantics, the definition should cover all three modes. It explains only supersede and invalidate, leaving forget_nugget (and its key parameter) completely unaddressed, which is a real gap for an agent choosing an action.

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 the baseline would be 3, but the description adds cross-parameter meaning: reason is tied specifically to invalidation and content to superseding, and lineage is introduced as a concept for supersede. It still says nothing about key or project semantics beyond the schema.

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 (revise) and resource (knowledge/memory) and names two of the three actions, supersede and invalidate, with the effect of each. It is clearly a mutation/revision tool distinguishable from remember and retrieve siblings, though the third enum value forget_nugget is never mentioned.

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

Usage Guidelines3/5

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

Implied when-to-use is present: supersede for stale knowledge, invalidate for obsolete rules. But there is no explicit routing guidance against krusch_context_remember (when to revise vs. add new) and no mention of when forget_nugget applies.

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