check_mx

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety and repeatability are covered. The description adds the derived provider-classification behavior and its role inside the scan_domain audit, but says nothing about caching, latency, or rate limits (the force_refresh parameter hints at caching only via the schema).

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?

Three tight sentences, front-loaded with the action, then the meaning of the output, then the usage triggers. No filler and nothing that repeats the title.

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 formatting need not be explained, and annotations carry the safety profile. Purpose, trigger conditions, and the audit-workflow relationship are all present, leaving nothing an agent needs before calling it.

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 description coverage is 100%: domain, format enum, and force_refresh are all documented in the schema itself. The description adds no parameter-level detail (no format values, no note that force_refresh matters after DNS changes), so the baseline 3 applies.

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 and resource ('Look up MX records for a domain') and then spells out what the result actually means: inbound mail servers plus the inferred email hosting provider. That inference (Google Workspace, Microsoft 365, Proofpoint) also implicitly separates it from the sibling check_mx_reputation, which is about reputation rather than configuration.

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 trigger conditions ('Use when asked which email provider hosts inbound mail for a domain, or to see MX record configuration') and places itself in the scan_domain audit workflow. It never states when NOT to use it or names a sibling to prefer instead, so it falls short of the top band.

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