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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds the operational consequences an agent can't infer: campaigns and conversations silently lose automated replies, prospects mid-conversation go unanswered, and knowledge attachments plus training are destroyed. It also discloses the required 'Agents' plan permission, which is not in the schema or annotations.

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?

Roughly five sentences, each doing distinct work: what it does, what breaks, irreversibility, the confirmation protocol, the non-destructive alternatives, the permission gate. The consequence is front-loaded before the guidance.

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?

For a one-parameter destructive mutation with no output schema, everything an agent needs is present: blast radius, irreversibility, a pre-flight confirmation workflow, alternatives, and the authorization requirement. Nothing material is missing.

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% and the single parameter already carries a description ('AI agent id, from `agent_list`'), so the baseline is 3. The description reinforces the `agent_list` provenance but adds no format or validation detail beyond the schema.

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 ('Delete an agent') and immediately distinguishes it from non-destructive siblings by naming the alternative paths (agent_upsert with isActive:false, conversation_update with assistant:false). An agent knows exactly what this does and what it costs versus those siblings.

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 explicit preconditions (read `agent_list`, show the user, get an explicit yes) and explicit when-not-to-use guidance that routes to two specific sibling tools for the softer cases. This is the strongest possible form of usage guidance.

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