evaluate_task_hierarchy

Read-only. Deterministically checks whether a task still supports its parent objective and reports invalid role ordering, missing intent, cycles, invalid lifecycle state, and active explicit conflicts.

Server Agentic Task System renezander030/agentic-task-system
Category Read
Risk class Low
Parameters 00 required

What evaluate_task_hierarchy does on Agentic Task System

AI agents call evaluate_task_hierarchy to retrieve information from Agentic Task System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why evaluate_task_hierarchy needs a policy

This is a read-only validation/analysis tool that inspects task hierarchy structure and relationships, returning diagnostic information about the state of tasks without side effects. It retrieves and analyzes data to report on consistency and validity, making it a Read category tool with low severity since misuse would only affect analysis results, not data or operations.

From the tool's definition Tool name is 'evaluate_task_hierarchy' and description explicitly states 'Read-only'. The function performs validation checks that report issues (conflicts, cycles, state problems) but do not modify, delete, or execute external operations.

Questions about evaluate_task_hierarchy

What does the evaluate_task_hierarchy tool do? +

Read-only. Deterministically checks whether a task still supports its parent objective and reports invalid role ordering, missing intent, cycles, invalid lifecycle state, and active explicit conflicts. It is categorised as a Read tool in the Agentic Task System MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on evaluate_task_hierarchy? +

Register the Agentic Task System MCP server in PolicyLayer and add a rule for evaluate_task_hierarchy: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Agentic Task System. Nothing to install.

What risk level is evaluate_task_hierarchy? +

evaluate_task_hierarchy is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit evaluate_task_hierarchy? +

Yes. Add a rate_limit block to the evaluate_task_hierarchy rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block evaluate_task_hierarchy completely? +

Set action: deny in the PolicyLayer policy for evaluate_task_hierarchy. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides evaluate_task_hierarchy? +

evaluate_task_hierarchy is provided by the Agentic Task System MCP server (renezander030/agentic-task-system). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.