build_dmarc_upgrade

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

Beyond annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses key behaviors: alignment gate derived server-side, caller cannot assert alignment, null cases are detailed, and the returned record must be approved by a human before publishing.

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 a single, information-dense paragraph with no wasted words. It is front-loaded with the main purpose. While very concise, it could benefit from slightly more structure (e.g., bullet points for null conditions) but remains clear.

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?

Given the tool's complexity (server-side derivation, multiple null cases, human approval requirement), the description covers all essential aspects: what is returned, when null occurs, how to handle the record (verbatim, human approval), and the semantic limits of the tool (caller cannot assert alignment).

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?

The schema has 100% coverage for the single parameter 'domain', and the description adds significant value by specifying accepted formats (bare registrable names and subdomains), forbidden components (scheme, path, port), and normalization (Unicode to punycode).

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 clearly states the tool returns a validated DMARC enforcement-upgrade record for a domain. It distinguishes itself from siblings like generate_dmarc_record and validate_dmarc_record by emphasizing that the upgrade is derived from a server-side scan and that the caller cannot assert alignment.

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 provides explicit when-to-use (requesting an upgrade record) and when-not-to-use (e.g., domain doesn't exist, DMARC lookup fails, domain already has sufficient policy). It also instructs to never compose a record to fill a gap and to present the returned record verbatim for human approval.

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