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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely new context: per-check pass/warning/fail results, an overall result, priority-ordered fixes with help links, an ~10 second runtime, and 'never changes DNS'. It does not discuss rate limits or how the auto-selector discovery can fail, so not a 5.

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?

Two tight sentences, front-loaded with the usage trigger, then the mechanics, return shape, timing and safety note. No filler and nothing repeated from the schema.

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 the return-value burden and does so: per-check statuses, an overall result, and prioritized fixes. Together with timing and the DNS-safety note, an agent has everything needed 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 coverage is 100%, so the baseline is 3, but the description adds real meaning about dkim_selector by explaining that DKIM discovery happens automatically ('finds the selector on its own'), telling the agent the optional param can generally be omitted.

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 (audits a domain) and enumerates exactly what it runs (SPF, DKIM, DMARC, blacklist, MX) 'in one call', which distinguishes it from the single-purpose siblings like spf_check and dkim_check. An agent can tell it is the aggregate deliverability tool 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?

Gives explicit triggering contexts: 'when the user asks why their emails go to spam' or 'wants a full deliverability check'. It implies use of the aggregate over individual checks but never names a sibling or states when NOT to use it, so it falls short of a full when/when-not/alternatives statement.

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