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

Adds substantial context beyond the destructiveHint/idempotentHint annotations: the required scope, the irreversibility ('cannot be undone'), and the non-obvious cascading behavior that monitors survive, become unowned (agent_id null), and keep running with history intact. That cascade is precisely what an agent needs before calling a destructive tool.

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

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

Two dense sentences with zero filler: authorization and irreversibility lead, then the monitor-survival consequence and the tools that handle survivors. Nothing is repeated or padded.

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

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

No output schema exists, and the description nevertheless explains the post-deletion state of dependent resources and which tools act on them. For a one-parameter destructive tool, an agent has everything needed to call it correctly.

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

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

Schema coverage is 100% for the single 'id' parameter, and the schema already documents that it is an agent UUID from register_agent or list_agents. The description adds only 'by UUID', so the schema does the heavy lifting and the baseline 3 applies.

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

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

States a specific verb and resource ('Permanently deletes an agent from the registry by UUID'), which cleanly separates it from get_agent, update_agent, and list_agents. The 'permanently' qualifier also distinguishes it from reversible mutations like update_agent.

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

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

Gives the prerequisite ('Requires the write scope or higher') and routes the agent for the follow-on case, naming update_monitor and delete_monitor for surviving monitors. It never explicitly says when not to use this tool (e.g. prefer update_agent to merely change an agent), so it falls just short of 5.

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