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

Annotations already declare readOnlyHint/destructiveHint=false, and the description reinforces this with 'Does not publish records or change DNS'. It adds genuinely new context: public DNS/policy lookups that may be cached, and that provider values/reporting addresses may require user input.

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?

Four tight sentences, front-loaded with purpose, then goal semantics, return contents, and behavioral caveats. No filler; each sentence carries distinct information.

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?

With no output schema, the description compensates by enumerating the returned artifacts (SPF, DKIM, DMARC, MTA-STS, TLS-RPT proposals, or provider setup instructions). An agent has enough to decide and invoke correctly.

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 schema already documents all three parameters. The description still adds value by stating baseline is the default when goal is omitted and that providers fall back to detection, which are not in the schema text.

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?

Names a specific verb (Propose/generate) and resource (email-authentication DNS records and policy files) with clear scope. It is unambiguous against siblings like get_dmarc_summary or diagnose_domain, which read rather than generate.

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: baseline (monitoring, p=none) vs enforce (quarantine/reject), with baseline as the default, and notes providers can be supplied or auto-detected. It does not explicitly route the agent away from siblings or state prerequisites, but the when-to-use context is solid.

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