check_dmarc

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so safety is covered structurally. The description adds the useful facts that it inspects live DNS and is a component of the scan_domain audit, giving the agent context about scope and relation to a larger workflow. It stops short of noting caching behavior, though the force_refresh param implies it.

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?

Front-loaded with the core action and scoped alternatives in three tight sentences. Slight redundancy between 'Shows the enforcement level (none/quarantine/reject)' and 'Use to determine a domain's DMARC enforcement level' repeats content without adding a new decision cue.

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?

Output schema exists, so return-value explanation is unnecessary, and annotations cover the safety profile. The description supplies purpose, output semantics at a high level, sibling disambiguation, and audit lineage, which is everything an agent needs to call 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 description coverage is 100% with three well-documented params, including the format enum and force_refresh purpose, so the schema carries the load. The description adds no parameter-level guidance such as when 'compact' vs 'full' is appropriate or when a refresh is warranted, so the baseline 3 is correct.

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?

States a specific verb+resource ('Look up and validate the DMARC record for a domain') and enumerates what is surfaced: enforcement level, alignment mode, and reporting destinations. It explicitly distinguishes itself from check_shadow_domains and assess_spoofability by name, so an agent can route correctly without opening 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?

Provides an explicit 'Use to determine...' clause with three concrete decision contexts (enforcement level, aggregate reporting, impersonation protection) and names the two nearest siblings it should not be confused with. Both when-to-use and the alternatives are stated, not inferred.

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