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

Annotations cover the safety profile (readOnly/idempotent/non-destructive), and the description adds substantial context beyond them: 10-minute result caching, a 30-new-checks-per-day-per-network rate limit, common-selector-only DKIM lookup, and the meaning of the `incomplete`/`unread` failure semantics. This is exactly the 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?

Purpose is front-loaded, followed by operational limits and interpretation caveats, each sentence earning its place. It reads as a dense run-on paragraph, but no content is redundant with structured fields.

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 carries return-value burden and does so well: the 0-100 score, fixes ordered most-severe-first, and the precise meaning of `dkim_not_found`, `incomplete: true`, and `unread`. An agent can interpret results correctly without any further documentation.

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 100% with a single documented `domain` parameter, so the schema already does the work and baseline is 3. The description reinforces the domain concept but adds no format or syntax detail beyond what the schema states.

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 (check) and resource (email sendability of a domain), then enumerates exactly what is probed: SPF, DKIM, DMARC, MX, MTA-STS, BIMI, plus the 0-100 score and fixes. It is unmistakably distinct from the CRUD-oriented sibling tools like email_domain_get or email_domain_verify.

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?

Clear context: 'Public DNS only. Free, no account,' establishing this as a no-auth diagnostic step. It does not name an alternative or state a when-not condition, but no sibling overlaps enough to require routing, so the missing exclusion is minor.

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