Delete DNS Records

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

Annotations already include destructiveHint:true and readOnlyHint:false. Description adds a warning that records are permanently removed and can break services, and explains the matching logic. This provides valuable behavioral context beyond annotations, such as the need for user confirmation and preview.

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 two sentences plus a warning, each sentence adding essential information without redundancy. The most critical information (action and matching logic) is front-loaded, followed by a clear warning. The structure supports quick comprehension.

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?

Given the tool's destructive nature, the description covers matching logic, prerequisites (list first), and user confirmation. No output schema is provided, but return values are not critical for a delete operation. A slight gap: does not mention idempotency (though annotation indicates idempotentHint:true).

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 provides descriptions for both 'domain' and 'records' (including item fields). Description clarifies that the matching is by name AND type together, which adds semantic precision beyond the schema. No contradictions or gaps.

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?

Description starts with 'Delete specific DNS records from a domain by name and type.' This clearly states the action (delete), resource (DNS records), and scope (by name and type). It distinguishes from sibling tools like list_dns_records and create_*_record tools, which are for different operations.

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?

Description specifies matching condition ('Only records matching both the name AND type will be removed') and advises to 'use list_dns_records first to verify which records will be deleted' and 'confirm with the user before calling.' This provides clear when-to-use and safety steps. Missing explicit mention of alternatives like save_dns_records for bulk replacement.

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