Skip to main content
Glama

krusch_context_revise

Idempotent

Supersede an evolving decision with a replacement and lineage, or invalidate an obsolete rule, keeping persistent agent memory accurate across sessions.

Instructions

Supersede an evolving decision with lineage or invalidate an obsolete rule.

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>",
      "target_id": "<target_id>"
    },
    "name": "krusch_context_revise"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
reasonNoReason for revision or revocation
target_idYesID of memory record to revise
provenanceNo
new_contentNoReplacement content when action is supersede

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.1

TDQS

C2.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered structurally. The description still adds real behavioral information beyond that: supersede preserves lineage while invalidate revokes, which tells the agent the two modes have different effects on the record's history. It stops short of explaining lineage mechanics, whether the superseded record remains retrievable, or what happens to a record's dependents after invalidation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single well-formed sentence with the two operation modes front-loaded and no wasted words. But for a two-mode mutation tool with five parameters and a nested object, this level of brevity reads as under-specification rather than discipline.

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

Completeness2/5

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

A non-read-only tool with two distinct action modes, a conditional parameter (new_content only under supersede), and a nested provenance object needs more than one clause of explanation, and there is no output schema to clarify effects. The description leaves out the record-retention consequences of each action and the action-dependent parameter coupling, which an agent must get right to call this correctly.

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 60%, with action, target_id, new_content and reason already documented inline in the schema. The description adds no parameter-specific meaning: it never mentions that new_content is only meaningful under supersede, nor what provenance is for. At 60% coverage the baseline of 3 applies, but the description does no compensating work for the nested provenance object, which has no field descriptions at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives two specific verbs, "supersede ... with lineage" and "invalidate," so the operations are identifiable. But the resource is described only abstractly as "an evolving decision" or "an obsolete rule"; the actual object being changed is a memory record (per target_id), and a reader would not know that this tool mutates the context/memory store. It does not name or contrast with siblings such as krusch_context_remember, so the purpose is discernible but not sharply bounded.

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 an implicit when-to-use signal in the split between superseding an *evolving* decision and invalidating an *obsolete* one, which is a genuine choice the caller must make. However, nothing states when this tool should be used instead of krusch_context_remember or a fresh write, nor any prerequisites such as needing an existing target_id. The caller is left to infer the routing.

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