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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds that the tool flags specific misconfigurations and that passing expected turns the call into an assertion, but it doesn't say which mistakes are flagged, what a mismatch yields, or how failures are reported.

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 sentences, no filler, with the core action and scope front-loaded and the optional-parameter behavior immediately after. Every clause carries information the agent can act on.

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 should carry return-shape information, yet it only gestures at 'flag the mistakes' without saying what the response contains (chain hops, error classification, pass/fail). For a low-complexity two-parameter read tool this is adequate but leaves a real gap on return values.

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% and both parameters carry descriptions, so the baseline is 3. The description only slightly extends the schema by framing 'expected' as an assertion ('assert where the chain should end up') versus the schema's neutral 'should resolve to'; it adds no format or failure-mode detail.

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?

The description names a specific verb+resource ('Follow a host's full CNAME chain') and adds the diagnostic intent ('flag the mistakes that break a cold-email tracking domain'), which tells the agent this is a CNAME-specific health check. It doesn't explicitly differentiate from close siblings such as check_dns, check_nameservers, or check_tracking_domain, so the agent must infer the boundary.

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?

'Pass expected to assert where the chain should end up' clarifies how to use the optional assertion mode, which implies verification use. However, there is no statement of when to prefer this over check_dns or check_tracking_domain, and no exclusions or prerequisites, so usage is only implied.

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