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

Annotations already declare readOnly/openWorld/idempotent, but the description adds materially more: it reads public DNS only, never connects to the domain's mail servers, and therefore cannot test SMTP TLS, certificates or mailbox existence, plus a typical runtime under 2 s. That explicitly bounds what the tool cannot prove, which is the failure mode an agent is most likely to hit.

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-loads the verb and scope, then usage, then behavioral limits. The long parenthetical enumeration of checks is dense but carries real scope information for a grading tool, so it mostly earns its space; it could be trimmed slightly without loss.

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?

An output schema exists so return values need not be explained, yet the description still tells the agent the grade levels (strong/fair/weak/no_mail/none) and that each check yields a status plus a one-line finding. Combined with the DNS-only limitation, an agent has everything needed to call it correctly and interpret results.

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?

Only one parameter and schema description coverage is 100%, so the schema already defines 'domain' including the 'not an email address and not a mail server host name' exclusion. The description adds nothing about the parameter beyond the schema, so the baseline of 3 is appropriate.

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 ('Grade') plus resource ('one domain's email authentication') and an explicit enumeration of the checks performed (SPF, DMARC, MTA-STS, TLS-RPT, BIMI, DANE, null MX). It also defines the grade vocabulary, and explicitly says lookup_target gives only the overall grade, so an agent can separate it from the sibling without opening either 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?

States the triggering contexts plainly ('questions about spoofing, deliverability or a DMARC rollout') and names the alternative tool plus the condition that should route to this one instead ('lookup_target gives only the overall grade; this tool gives the status and a one-line finding for each check'). Nothing is left to inference.

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