7IT Solutions

Map what an AI agent may do on its own

map_agent_oversight

Read-onlyIdempotent

Use this when someone asks which actions their AI agent or its connected tools may take on their own, which need a person's approval, and which a person must do; or how to set up human oversight, permissions or AI governance for an agent (for example under the EU AI Act). Give either the address of a public MCP server, or the list of tools the agent has (name, description and annotations). Sorts every tool into green (runs alone: reads and prepares), yellow (a person approves: sending, updating, scheduling) or red (a person does it: money, permissions, deletion, code execution, commitments), flags tools with no risk annotations, and returns a ready policy, Claude Code permission rules (allow, ask, deny) and an oversight checklist. Reads tool lists only and never calls a tool. A working checklist, not legal advice.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "map_agent_oversight"
  }
}

Input Schema

Name	Required	Description
`url`	No	The MCP server address, for example https://mcp.example.com/mcp
`tools`	No	Instead of an address: the tools the agent has, with their description and annotations
`server_name`	No	The name this server has in the agent setup, used in the Claude Code permission rules

Output Schema

Name	Required	Description
`red`	No	Tools a person should do themselves
`green`	No	Tools the agent may run on its own
`tools`	No
`total`	No
`server`	No
`yellow`	No	Tools that need a person to approve
`checklist`	No
`unlabeled`	No	Tools whose server publishes no risk annotations
`report_url`	Yes	Shareable page with the full map
`claude_code_permissions`	No	Paste into .claude/settings.json

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 1, 2026

TDQS

A4.9/5.0

Behavior5/5

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, but the description adds crucial behavioral context beyond annotations: it explains the green/yellow/red classification scheme, that it flags tools with no risk annotations, that it returns a policy, Claude Code permission rules, and an oversight checklist, and explicitly states it reads tool lists only and never calls a 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 dense but well-structured: it front-loads the when-to-use, then input options, then outputs and classification. Every sentence adds distinct value with no repetition, ending with a clear disclaimer.

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

Completeness5/5

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

Given the tool's complexity, the description covers purpose, usage, inputs, outputs, classification logic, and behavioral constraints. An output schema exists, so return values needn't be detailed, and the agent has everything needed to invoke correctly.

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 parameters are already documented. The description adds meaning by explaining that 'url' is an alternative to 'tools' and that 'tools' is a list with name, description, and annotations. It doesn't specify the exact format for Claude Code permission rules or how server_name is used, but it goes beyond the schema.

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

Purpose5/5

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

The description names a specific verb (map) and resources (AI agent actions, tools, oversight levels) and clearly distinguishes this from sibling checks like check_app_security or deep_scan_app by focusing on agent governance. An agent can immediately tell what this tool does.

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

Usage Guidelines5/5

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

It gives explicit triggers: when someone asks which actions their AI agent may take alone, which need approval, or how to set up oversight/permissions/governance (with EU AI Act example). It also specifies exactly what input to provide: a public MCP server address or a list of tools with name, description, and annotations.

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

All 7IT Solutions tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?