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

Annotations already cover readOnly/idempotent/openWorld, so the description's added value is the disclosed cost model ($0.002 per call) and the shape of the result (grade, verdict, plain-English issues) — useful context beyond structured fields. It stops short of rate limits, caching, or failure behavior.

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?

One front-loaded sentence that names the resource first, enumerates checks, then states outputs and price. No redundant or filler text.

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 helpfully lists what comes back (grade, spoofability verdict, issues) and the per-call price, which is enough for an agent to decide and invoke. A minor gap is the absence of any mention of latency, failure modes for unresolvable domains, or result size.

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?

Single parameter with 100% schema description coverage including an example ('github.com'), so the schema carries the semantics fully. The description adds nothing parameter-specific, which is acceptable at this baseline.

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?

Specific verb ('Audit') plus specific resource ('domain's email security'), and it enumerates the exact checks performed (SPF, DMARC, DKIM, MX, MTA-STS, TLS-RPT, BIMI) along with the outputs (A-F grade, spoofability verdict, plain-English issues). This clearly separates it from siblings like dns_lookup or security_headers, which cover narrower slices.

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 scope implies when to use it (auditing a domain's email posture), but there is no explicit 'use this instead of dns_lookup / security_headers / domain_report' routing guidance and no stated exclusions. Usage is inferable but not directed.

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