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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds some behavioral context — fix_plan can bypass cache and run a fresh scan, mta_sts_policy can detect MX hosts from DNS (live network access) — but says nothing about output form, determinism, or cost of a fresh scan.

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?

Two sentences, front-loaded with the core action before the artifact taxonomy; every gloss carries information rather than repeating the enum. The dense inline enumeration is slightly harder to scan than a short bullet list would be, but nothing is wasted.

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 an 11-parameter tool with no output schema and no annotations about return values, an agent still cannot predict the shape of the response — a raw DNS record string, a JSON plan, or a multi-file bundle — nor whether generated artifacts are returned for copy-paste or stored server-side. The inputs are well covered, the output side is not.

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 description coverage is 100%, so the baseline is 3, and the description earns above that by explaining what each artifact enum value produces and thereby which parameters become relevant (policy/rua_email for dmarc_record, timeline/target_policy for rollout_plan). It stops short of describing defaults for format auto-detection or how include_providers interacts with SPF record construction.

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 (generate) and resource (DNS/email security remediation artifact) and enumerates the six artifact types with a one-line gloss for each, so an agent knows exactly which output it will get. It is clearly distinguishable from the check_*/analyze_* siblings that inspect rather than produce artifacts.

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?

"Use when asked to generate or create a record or policy" gives a clear trigger condition, and the artifact list implicitly routes the agent among variants (e.g., fix_plan vs. rollout_plan). It does not name alternatives or exclusions, such as deferring to validate_fix to check a generated artifact or to the check_* tools when the user wants an audit rather than an artifact.

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