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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description goes beyond them with genuinely useful semantics: what 'sent' actually means (provider acceptance, not host read), where email replies land (the approved reply email), and an explicit statement that no send or retry occurs. That interpretive context is exactly the kind of value a status tool needs; only the set of possible status values is left undocumented.

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?

Four short sentences, front-loaded with the core action, each adding a distinct fact (what is read, meaning of 'sent', reply routing, no send/retry). No filler, though the final sentence partially overlaps with the read-only framing already implied.

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 and annotations covering safety, the description must carry the semantic load, and it does: it explains the key status value and reply routing. It would be fully complete if it enumerated the possible status values or indicated what the response contains, but for a one-parameter read tool it is close to sufficient.

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 0% for the single required requestId, and the schema only supplies a 64-char hex pattern with no explanation. The description says the request is 'your own' but never explains what requestId identifies, where it comes from, or its format, so it fails to compensate for the coverage gap.

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 ('Read your own host-contact request') and scopes it to the caller's own request, which cleanly separates it from the send/prepare host-contact siblings. The closing line ('This read does not send or retry a message') pins down what the tool is not, so an agent can distinguish it from send_host_contact 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?

It implies the use case (checking the status of an already-sent request) and gives one implicit exclusion by stating it does not send or retry, which steers an agent away from using it as a resend mechanism. However, it never names an alternative sibling or states conditions under which the agent should read this versus, say, inspect_email_replies, so guidance remains implied rather than explicit.

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