Import DNS zone

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

Goes well beyond the annotations (destructiveHint=true) by disclosing impact ('can change public DNS answers after publication'), the exact record types skipped or rejected (PTR/reverse, SOA, DNSSEC wire records, apex NS, LUA), and the required scope. This is exactly the extra context annotations cannot carry.

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?

Front-loaded with purpose, then semantics, then exclusions, then auth. Information-dense with minimal waste, though it is a fairly dense multi-clause block rather than truly compact.

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, no-output-schema mutation tool, it covers impact, parameter semantics, unsupported inputs, and permissions — everything an agent needs to call 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 coverage is 100%, so baseline is 3, but the description adds real meaning: replace=true replaces non-system desired-state records while false upserts them — the 'upserts' behavior is not in the schema text.

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?

Specific verb (Import) plus resource (BIND-style forward DNS records into a native zone), and it explicitly bounds scope to forward records rather than reverse. An agent can distinguish this from upsert_dns_record/update_dns_record at a glance.

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?

Clearly states the replace=true vs false behavior and the auth requirement (dns:write), and enumerates what is skipped/rejected by the API. It does not explicitly route to sibling tools (e.g. upsert_dns_record for single records), so it stops short of full alternative guidance.

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