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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: accepted encodings and container formats, the fact that no network lookups occur, the exact output sections produced, and a per-call price with an x402/Solana payment requirement plus an HTTPS endpoint. Cost and payment prerequisites are exactly the kind of operational detail annotations cannot express.

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?

Input formats come first, then the two report-type output breakdowns, then constraints and cost. The enumerated field lists (pass rates, dispositions, per-source verdicts) earn their space because no output schema exists to carry that 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 well by enumerating the return fields for both DMARC and TLS-RPT, plus behavioral constraints and pricing. The remaining gap is `maxSources`: an agent cannot tell from the description whether results are capped or how to raise the cap, which matters for reports with many sending IPs.

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 50%: `report` is documented in the schema and the description usefully restates its accepted formats (raw XML/JSON or base64 of .xml/.gz/.zip). However, `maxSources` (default 100, max 500) is never mentioned, so the description neither explains what it limits nor warns that the advertised 'every sending source IP' may be truncated. Baseline 3 is appropriate at this coverage level.

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 concrete verb (parse) plus the exact resources (DMARC aggregate RUA reports and SMTP TLS reports per RFC 8460) and what it turns them into (an actionable summary). An agent can distinguish this from generic email/DNS siblings without opening the schema.

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?

Describes the input conditions clearly (.xml, .xml.gz, .zip, raw XML/JSON, base64) and explicitly rules out a competing approach with 'No DNS or network lookups,' which separates it from dns_propagation/dns_dump-style siblings. It stops short of naming a specific alternative tool or stating when not to use it.

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