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

Annotations already flag destructiveHint/idempotentHint, but the description goes further: it discloses immediate DNS propagation risk, that the prior RRset is read and returned as `previous` for undo, the refusal of empty record lists, immutable apex NS/DNSSEC, rate limits, and the underlying PUT endpoint shape.

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?

A single dense paragraph, front-loaded with the destructive WRITE marker and the exact effect, then risk, reversibility, failure modes, limits. No sentence is filler.

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 write tool, the description covers effect, reversibility (previous returned), failure conditions, protected records, and quotas. An agent has everything needed to call it safely without additional context.

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 ttl, records, subname, and type semantics are already documented in the schema. The description adds only the one-element-array/PUT framing and the `previous` return behavior, so the baseline 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?

States a precise verb+resource+scope: 'set ONE RRset to exactly the given TTL and records'. This distinguishes it from desec_create_rrset (create-only) and desec_get_rrset/desec_list_rrsets, and the WRITE (overwrites) marker front-loads the operation class.

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?

Gives clear context: creates if absent, replaces if present, refuses empty lists, cannot touch apex NS/DNSSEC, and cites write limits (15/min, 300/day). It does not explicitly name desec_create_rrset as the alternative when you only want to add without replacing, which is the one routing gap.

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