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

Beyond the destructiveHint annotation, the description discloses that the tool only stages deletion, is irreversible once executed, returns an actionId, and requires a follow-up confirmation call. This significantly enriches the agent's understanding of the tool's non-immediate and gated destructive behavior. No contradiction with annotations; idempotentHint is consistent with staging.

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?

The description is a single, dense sentence that front-loads the purpose, includes critical warnings, and provides the action flow. Every clause adds value without redundancy. It is concise and well-structured for an agent to parse quickly.

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?

The description covers the essential flow: staging, confirmation, and execution. It states the return value (actionId) and the next step. It doesn't elaborate on what the summary should contain or what happens if the user declines, but these are minor gaps given the tool's simplicity and the presence of annotations.

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?

The description adds no parameter-specific meaning, but the input schema provides complete descriptions for all three parameters, including examples and context (e.g., recordId references listDnsRecords, sessionKey explains when to include). Since schema coverage is 100% and descriptions are thorough, the baseline of 3 is appropriate.

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 description clearly states the tool stages the deletion of a DNS record, distinguishing it from create/update operations. It specifies the resource and action precisely, and the warning 'DESTRUCTIVE and irreversible once executed' adds critical purpose context. The sibling list includes createDnsRecord and updateDnsRecord, so this purpose is unambiguous.

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?

The description explicitly instructs the agent to present the summary and call executeConfirmedAction if approved, providing a clear two-step usage flow. It does not explicitly contrast with alternatives like updateDnsRecord, but the deletion intent is obvious. The 'Requires authentication' note is generic but not misleading.

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