Build DMARC Upgrade Record

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

With annotations only declaring safety flags, the description carries real behavioral weight: the alignment signal is derived server-side and cannot be asserted by the caller, np=reject is injected unless an np tag already exists, a null record is a legitimate answer with enumerated causes, and the record must be presented verbatim pending human approval. None of that is recoverable from readOnlyHint/destructiveHint/openWorldHint.

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?

It is correctly front-loaded — the triggering situations come first, then the return contract, then the null-case rules. The content mostly earns its place, though the long parenthetical null-case enumeration and semicolon-chained clauses make it dense and harder to scan than a short bulleted breakdown would be.

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 one-parameter tool with no output schema, the definition covers the decision logic, the np-tag behavior, and how to treat a null record. The only real gap is that a returned record's shape is never sketched (only `rationale` is named), leaving the agent reliant on 'present verbatim' to handle 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 single `domain` parameter is already fully documented in the schema (bare registrable names, subdomains, punycode normalization). The description adds only the phrase 'for a domain' and no extra syntax or constraint detail; baseline 3 applies when the schema does the work.

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 gives a specific verb and resource — 'Return a validated DMARC enforcement-upgrade record for a domain' — and immediately bounds what such a record can be (scan justifies at most p=quarantine; p=reject requires aggregate-report monitoring evidence). That framing separates it from a generic record builder or a raw domain scan without the agent needing the sibling schemas.

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?

It opens with explicit triggers ('when the user asks how to move DMARC on from p=none, whether it is safe to tighten DMARC, or what the next DMARC policy step is') and adds a second condition ('after any report showing DMARC below enforcement'). It also enumerates the when-not cases via the null-record list and warns 'never compose a record to fill the gap,' which is a usable exclusion rule rather than inference.

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