Skip to main content
Glama
openhoat

aik-mcp

by openhoat
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

uninstall

Remove a content item's file and its config reference from your project or global setup for AI agents like opencode, Claude Code, Cline, and Codex.

Instructions

Uninstall a content item from the current project. Removes the file and the config reference. Supports opencode, Claude Code, Cline, and Codex.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesPath of the content to uninstall (e.g. "rules/typescript")
agentYesTarget AI agent (opencode, claude-code, cline, codex, or copilot).
scopeNoInstallation scope (project or global).project
projectDirNoProject directory (defaults to current working directory). Config files are found by walking up.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.0
    • addedInput schema / properties / scope
      Added value: +{
+  "default": "project",
+  "description": "Installation scope (project or global).",
+  "enum": [
+    "project",
+    "global"
+  ],
+  "type": "string"
+}
  2. Changed3 schema fields changedv0.3.1
    • changedInput schema / properties / agent / description
      Previous value: -"Target AI agent. Auto-detected from existing config files if not specified."New value: +"Target AI agent (opencode, claude-code, cline, codex, or copilot)."
    • changedInput schema / properties / agent / enum
      Previous value: -[
-  "opencode",
-  "claude-code",
-  "cline"
-]New value: +[
+  "opencode",
+  "claude-code",
+  "cline",
+  "codex",
+  "copilot"
+]
    • changedInput schema / required
      Previous value: -[
-  "path"
-]New value: +[
+  "path",
+  "agent"
+]
  3. Addedv0.1.1

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the core side effect (file + config reference removed), which is real value. It omits reversibility, error behavior when the item isn't installed, and permission requirements, and its supported-agent list (opencode, Claude Code, Cline, Codex) silently drops copilot, which the schema's enum includes.

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?

Three short sentences, front-loaded with the action and resource, then the side effect. No padding, though the trailing agent-support sentence is the weakest and partially redundant with the schema enum.

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?

A mutation tool with no annotations and no output schema; the description adequately covers what it does and what changes, and the schema is fully documented. It falls short on error/edge-case behavior and on routing among the several removal-related siblings.

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 description coverage is 100%, so the schema already documents all four parameters (path, agent, scope, projectDir) including the config-walking fallback behavior. The description adds no parameter meaning and its agent enumeration is actually less accurate than the enum, so baseline 3 rather than higher.

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 and resource ('Uninstall a content item') and clarifies the effect ('removes the file and the config reference'). However, it never distinguishes itself from close siblings like delete and uninstall_all, leaving the agent to guess which removal tool to pick.

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?

No when-to-use guidance, no prerequisites, and no named alternatives, despite delete, uninstall_all, and reinstall being present as siblings. The agent must infer the selection criteria entirely.

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

Deploy Server

Other Tools