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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered and the description only needs to add context. It does add per-artifact behavior (a fix_plan is 'prioritized' across 'all findings', a rollout_plan is a 'phased' timeline), but it never says whether output is a copy-pasteable record, whether missing inputs trigger DNS lookups, or how the artifacts relate to each other.

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?

The description is front-loaded with the core action and the artifact taxonomy, with no filler or marketing language. The final 'Use when asked to generate or create a record or policy' sentence partly restates the opening verb, a minor redundancy in an otherwise tight definition.

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, the description covers input intent well but says nothing about what comes back — a record string, a file, a structured plan with steps? With no output schema to lean on, that is a real gap for an agent deciding whether to call this or a check_* tool first. The per-artifact guidance is sufficient to pick the right artifact value, which keeps it at adequate rather than poor.

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, but the description adds meaning beyond the terse enum label in the schema ('Which artifact to generate') by explaining what each artifact type actually produces. It does not, however, explain the modality rules that the schema implies — that policy/rua_email only apply to dmarc_record, mx_hosts to mta_sts_policy, provider to dkim_config — leaving an agent to infer which params are relevant per artifact.

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?

The description names a specific verb (generate) and resource (DNS/email security remediation artifact) and then enumerates every artifact type with a short gloss, e.g. 'spf_record (build a new SPF record)' and 'rollout_plan (phased DMARC enforcement timeline)'. That lets an agent distinguish this generator from the surrounding check_* inspection tools without opening the schema.

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 positive trigger, and the implicit contrast with the abundant check_* siblings is reinforced by the fact that this tool emits artifacts rather than inspecting them. It stops short of stating exclusions, e.g. that pre-existing record inspection belongs to check_dmarc/check_spf, so it is strong but not fully explicit.

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