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

Annotations only declare readOnlyHint=false, so the description carries real weight and does: idempotent retry behavior ('same idempotency_key returns the same activation'), no-op semantics and no charge when already on, and free deactivation. That is exactly the billing and retry context an agent needs before a mutating call.

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?

Four short sentences, front-loaded with the action, then precondition, then edge-case behavior. No filler; the capability tag at the end is compact and useful.

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 four-parameter mutating tool with no output schema and thin annotations, this covers preconditions, idempotency, and charging edge cases well. It does not describe the shape of a successful first activation (fields returned, what 'current activation' contains), which would help the agent use the result.

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 only 25% (company only), so the description must compensate and largely does: quote_id is tied to the confirmed quote, idempotency_key is described as unique and retry-stable, and 'on' is explained via its on/off semantics. It leaves open whether quote_id is required specifically when turning on versus off, which the schema does not clarify either.

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?

The opening sentence gives a specific verb and resource ('Turn Attack Mode on or off') with a boolean toggle, which is unambiguous. It does not name or contrast itself with the sibling quote_attack_mode, so an agent must infer the quote-to-activation flow rather than being told.

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?

It states the precondition for turning on ('only after the person said yes to the quote's confirmation'), which identifiers to pass ('that quote_id and a unique idempotency_key'), and that exit is free. Implicitly orders the agent against quote_attack_mode by requiring a prior quote confirmation.

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