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

Annotations mark this destructive and open-world, but the description goes well beyond them: it warns the change goes live as soon as NS1 serves it and that a wrong answer can take a site or mail offline. It also discloses the existence check and refusal behavior, which no annotation conveys.

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-loads the write/live-DNS risk, then the scope limits, then the alternative, then the rdata formats. Every clause carries information, including the PUT endpoint, and the example lists are compact rather than padded.

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 this covers the risk, the type boundary, the conflict behavior, the alternative tool, and the exact rdata shapes an agent must construct. Nothing needed to call it correctly is missing.

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 schema defers the hardest parameter to the description ('each a list of rdata fields (see the tool description)'), and the description pays that off with concrete per-type examples for A, MX, TXT, SRV, and CAA. That is real added meaning, though ttl and zone/domain formatting are left to the schema.

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?

Opens with a specific verb and resource ('WRITE: creates ONE new DNS record') and immediately scopes the effect ('CHANGES LIVE DNS for that name'). It distinguishes itself from the sibling ns1_update_record by naming it in the refusal case, so an agent can route correctly without reading schemas.

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?

States explicitly when it refuses ('when the record already exists') and names the correct alternative ('use ns1_update_record'). It also bounds applicability by listing supported record types and explicitly excluding NS/SOA and traffic-steering filters/metadata, so the when-not is as clear as the when.

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