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

While annotations already declare destructiveHint=true and readOnlyHint=false, the description adds irreversibility, immediate removal from the live site, and the preview-before-confirm behavior. These details go well beyond the structured annotations and are critical for safe use.

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?

Three sentences, all substantive: the destructive claim, the real-world consequence, and the safe calling pattern. No filler or repetition; key warnings are front-loaded.

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 destructive two-parameter tool with no output schema, this description covers purpose, impact, irreversibility, and a precise two-step confirmation flow. It even hints at what the first call returns ('see exactly which chatbot would go'), so an agent has enough context to invoke it safely and 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 description coverage is 100%, with both domain and confirm already documented. The description adds value by explaining the confirm=false preview step and the rule that confirm=true must never appear on the first call, but the schema already covers the core meaning of each parameter.

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?

Starts with 'PERMANENTLY delete a website chatbot,' a specific verb and resource, and distinguishes this destructive operation from sibling tools like rename_chatbot, update_chatbot_links, and create_website_chatbot. The immediate live-site impact further clarifies what deleting means.

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?

Provides explicit call protocol: first call without confirm to preview, show the user, get explicit consent, then call with confirm=true, and never pass confirm=true on the first call. This is strong, actionable guidance that removes ambiguity about when and how to invoke the tool.

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