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

Although annotations already declare destructive=false/readOnly=false, the description adds critical context the annotations cannot: changes go live in DNS immediately, a wrong record can take a site or mail offline, it never touches apex NS or DNSSEC records, and it cannot delete anything. It also discloses concrete write rate limits (15/min, 300/day per domain).

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 'WRITE:' so a scanning agent immediately sees the risk class, then packs failure modes, side effects, restrictions, and rate limits into a few dense sentences. No filler and no repetition of what the schema or annotations already say.

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 non-idempotent, destructive write with no output schema, the description supplies the failure conditions, the immutability boundaries (NS/DNSSEC untouched, cannot delete), the rate limits, and the conflict semantics. An agent has everything needed to decide and invoke safely.

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 baseline is 3, but the description adds real interpretive value by explaining that the uniqueness key is the combination of subname and type, and the destination endpoint POST /domains/{name}/rrsets/. It stops short of restating ttl/records formatting, which the schema already covers.

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?

States a specific verb and resource ('create ONE new RRset') and immediately defines the domain concept in parentheses, so the agent knows exactly what object is produced. It also distinguishes itself from the sibling desec_replace_rrset by naming the failure mode that routes there.

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?

Explicit routing: 'Fails if an RRset with this subname and type already exists (use desec_replace_rrset for that).' It also states when it will fail on CNAME conflicts, giving clear when/when-not guidance rather than leaving the agent to guess between create and replace.

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