world-model-mcp

record_correction

Log user corrections to AI outputs as high-priority learning signals, capturing session context, AI actions, and correction reasoning to refine future model behavior.

Instructions

Record a user correction to Claude's output (high-priority learning signal)

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": {
      "session_id": "<session_id>",
      "claude_action": "<claude_action>",
      "user_correction": "<user_correction>"
    },
    "name": "record_correction"
  }
}

Input Schema

Name	Required	Description
`reasoning`	No	Inferred reason for the correction
`session_id`	Yes
`claude_action`	Yes	What Claude did (tool, file, content)
`user_correction`	Yes	How the user corrected it

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.7.3May 27, 2026

TDQS

C2.8/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the action is a 'high-priority learning signal', which hints at importance but does not describe side effects, persistence, reversibility, permissions, or any consequences of invoking the tool. This is a significant gap for a mutation-like recording tool.

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

Conciseness5/5

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

The description is a single, grammatically complete sentence of about ten words. It is front-loaded with the core verb and resource, and the parenthetical adds context without redundancy. Every word earns its place; there is no fluff or tail-heavy content.

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?

The tool involves nested object parameters, no annotations, and no output schema, yet the description stays at a high level. It does not explain how to structure claude_action or user_correction, what counts as a valid correction, or what the tool returns. This leaves an agent under-informed for correct invocation, especially given the complexity of the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 75%, and the description adds no additional meaning beyond what the schema already provides. The phrase 'user correction to Claude's output' loosely maps to claude_action and user_correction but does not clarify their structure or relationships. The 'reasoning' and 'session_id' parameters are not addressed at all in the description.

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 uses a specific verb ('Record') and identifies the resource ('a user correction to Claude's output'), which clearly conveys the tool's function. The parenthetical '(high-priority learning signal)' adds useful context. However, it does not explicitly differentiate from sibling tools like record_event or record_decision, though 'correction' provides some distinction.

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 description implies the tool should be used when a user corrects Claude's output, but it gives no explicit 'when to use' vs. alternatives, no exclusions, and no prerequisites. Sibling tools with overlapping purposes (e.g., record_event, record_decision) are not referenced, leaving the agent without clear selection criteria.

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