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

Annotations already flag destructiveHint=true, but the description adds what exactly is destroyed (rules, whole firing history), that it cannot be undone from the portal, and which reversible alternative preserves history. This is substantial behavioral context beyond the generic annotation.

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?

Five short sentences, front-loaded with the destructive consequence, then the safer alternative, then the narrow usage condition and the id workflow. No filler; every sentence earns its place.

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, non-idempotent, single-parameter tool, the description covers consequences, reversibility, alternatives, when-to-use, and how to obtain and confirm the id. With no output schema required, 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%, so the alert_id UUID and its source are already documented. The description still adds a useful operational layer: use list_alerts to find the id and name the alert in the confirmation, reducing the risk of deleting the wrong resource.

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?

Names a specific verb and resource ('delete one alert definition') and specifies the full scope, including all rules and the alert's firing history. The contrast with set_alert_enabled later makes it easy to distinguish from 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?

Explicitly names set_alert_enabled with enabled=false as the alternative for a noisy alert and states the narrow condition for using delete_alert. It also covers the mistake-undo scenario, giving very clear when-to-use and when-not-to-use guidance.

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