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

Goes well beyond the annotations: explains the real-world risk of policy choices (reject silently destroys legitimate mail), states that it returns warnings covering deployment mistakes, refuses invalid rua/ruf/pct entries with an error, and explicitly notes that nothing is looked up or stored. This is fully consistent with readOnlyHint, idempotentHint, and destructiveHint=false.

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 longer than average, but almost every clause earns its place given the policy risk and nine optional parameters. It is front-loaded with the core purpose and the key caution ('The risk here is not syntax but policy'), then covers returns and validation. It could be tightened slightly, but it is not bloated.

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 tool with no output schema and nine optional parameters, this description fully covers what the tool returns (record, host, warnings), how it behaves on invalid input, side effects (none), and the deployment context needed to use it safely. An agent has enough to select and invoke it 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 baseline is 3. The description adds meaningful policy-level semantics for the most consequential parameters: p=none/quarantine/reject tradeoffs, the requirement for rua, pct having no effect at p=none, and strict alignment breaking subdomain senders/ESPs. This enriches the schema without duplicating it.

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 and resource ('Build a DMARC record — the `_dmarc` TXT record') and explains exactly what the record does: tell receivers how to handle SPF/DKIM failures and where to send reports. This sharply distinguishes it from sibling tools like check_dmarc (inspection) and generate_spf (different record type).

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?

The description gives strong context on when to use different policy settings: start with p=none, only enforce after reports show alignment, use percentage for gradual rollout, and always publish rua. However, it never explicitly names sibling tools or states when not to use this tool versus alternatives, so it stops short of full exclusion guidance.

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